From 50750f652763795bcfac0696cca46436e4bd22db Mon Sep 17 00:00:00 2001 From: Emanuela Boros Date: Wed, 29 Oct 2025 10:44:43 +0100 Subject: [PATCH 1/7] experiments notbook documented --- examples/notebooks/experiments.ipynb | 3676 +++++++++++++++++++++++++- 1 file changed, 3601 insertions(+), 75 deletions(-) diff --git a/examples/notebooks/experiments.ipynb b/examples/notebooks/experiments.ipynb index dcdeef3..357bf17 100644 --- a/examples/notebooks/experiments.ipynb +++ b/examples/notebooks/experiments.ipynb @@ -1,9 +1,49 @@ { "cells": [ + { + "cell_type": "markdown", + "id": "8925620d-a388-4e65-948d-2dbb8110da50", + "metadata": {}, + "source": [ + "# Exploring Sentence, Chunk, and Entity Embeddings for Retrieval \n" + ] + }, + { + "cell_type": "markdown", + "id": "f9b62617-ad8b-4a17-92f7-02bf97ac173f", + "metadata": {}, + "source": [ + "This notebook provides a **proof of concept (PoC)** for working with embeddings in the *Impresso* corpus across three levels of granularity: \n", + "\n", + "1. **Sentence embeddings** – fine-grained retrieval at the level of individual sentences (e.g., `lepetitparisien-1912-11-13-a-i0001-s-11`). \n", + "2. **Chunk embeddings** – broader retrieval at the level of aggregated text chunks (e.g., `lepetitparisien-1912-11-13-a-i0001-c-1`). \n", + "3. **Entity embeddings** – retrieval of linked entities (e.g., `Q380083` or `Jonas Furrer`). \n", + "\n", + "We refer to sentences and chunks as _subdocuments_ and we test these *subdoc* embeddings with two complementary query scenarios: \n", + "\n", + "- **In-corpus queries** – selecting a query directly from the *Impresso* corpus. \n", + "- **Out-of-corpus queries** – embedding an external query (e.g., manually formulated or from another source). \n", + "\n", + "For the purpose of this PoC:\n", + "\n", + "👉 The **subdocs** = sentence and chunk embeddings for **front pages** of all newspapers in **1912 (Titanic)** and **1986 (Tchernobyl)**. \n", + "👉 The **entities** = entity embeddings for **person entities** in the years [+/- 5y] around the same years.\n", + "\n", + "From now on, we refer to this PoC as a set of **experiments**. The experiments use direct queries to our internal retrieval system ([Solr](https://solr.apache.org/))." + ] + }, + { + "cell_type": "markdown", + "id": "a8f950b1-132d-4e96-8b24-6d7ef3205f44", + "metadata": {}, + "source": [ + "Let's first connect to Impresso:" + ] + }, { "cell_type": "code", - "execution_count": 1, - "id": "4298569e", + "execution_count": 32, + "id": "babd8f0e-b1fd-4000-8bd4-386fbdf83da8", "metadata": {}, "outputs": [ { @@ -11,14 +51,14 @@ "output_type": "stream", "text": [ "🎉 You are now connected to the Impresso API! 🎉\n", - "🔗 Using API: http://localhost:3030\n" + "🔗 Using API: https://dev.impresso-project.ch/public-api/v1\n" ] } ], "source": [ "from impresso import connect\n", "\n", - "impresso = connect()" + "impresso = connect('https://dev.impresso-project.ch/public-api/v1')" ] }, { @@ -31,7 +71,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 33, "id": "509603ee", "metadata": {}, "outputs": [ @@ -41,7 +81,7 @@ "
\n", "
\n", "

FindExperiments result

\n", - "
Contains 1 items of 1 total items.
\n", + "
Contains 2 items of 2 total items.
\n", "
\n", "
\n", "
\n", @@ -79,15 +119,20 @@ " Experiment with sentence and character level e...\n", " \\n Generates embeddings for subdocuments usin...\n", " \n", + " \n", + " entity-profiles\n", + " Experiment with entity profiles and their embe...\n", + " \\n Generates embeddings for subdocuments usin...\n", + " \n", " \n", "\n", "" ], "text/plain": [ - "" + "" ] }, - "execution_count": 8, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" } @@ -101,64 +146,933 @@ "id": "aa567e33", "metadata": {}, "source": [ - "### Word/Character embeddings experiment" + "### Subdoc Embeddings Experiments" + ] + }, + { + "cell_type": "markdown", + "id": "4969dfde-1089-45c2-bea1-f99c3de2118b", + "metadata": {}, + "source": [ + "#### Sentence Embeddings - In-corpus queries\n", + "\n", + "Let's search for some documents, take their embeddings and then search by embedding in Impresso." ] }, { "cell_type": "code", - "execution_count": 32, - "id": "df2b9dab", + "execution_count": 34, + "id": "5ef16862-23ad-4447-be29-49be71260333", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Got 1 solr documents\n" + "✅ Got 5 Solr document(s)\n", + "\n" ] } ], "source": [ + "sentence = \"Le congrès international s'est tenu à Paris pour discuter des avancées scientifiques de la décennie.\"\n", + "\n", "result = impresso.experiments.execute(\n", - " experiment_id=\"subdoc-embeddings\",\n", - " body={\n", - " \"solrPayload\": {\n", - " \"query\": \"content_txt_fr:chat AND type_s:s\",\n", - " \"limit\": 1,\n", - " \"params\": {\n", - " \"hl\": False\n", - " }\n", + " experiment_id=\"subdoc-embeddings\",\n", + " body={\n", + " \"solrPayload\": {\n", + " \"query\": f\"content_txt_fr:({sentence}) AND type_s:s\", # type_s:s restricts search to sentences\n", + " \"limit\": 5,\n", + " \"params\": {\"hl\": False}\n", + " }\n", " }\n", - " }\n", ")\n", - "print(f\"Got {len(result['solrResponse']['response']['docs'])} solr documents\")" + "\n", + "docs = result[\"solrResponse\"][\"response\"][\"docs\"]\n", + "print(f\"✅ Got {len(docs)} Solr document(s)\\n\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "id": "df2b9dab", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "--- Result 1 ---\n", + "Mais c’ est une question qui ne peut se régler en congrès internationaux et c’ est pourquoi le pays cjui ne présente pas une natalité suffisante sera étranglé, ce qui ne sera d’ ailleurs qu’ une avance sur son sui- cide.\n", + "--- Result 2 ---\n", + "ÉDITION DE PARIS Les Eves nouvelles Les suffragettes françaises on * tenu, dimanche, une réunion où fut discutée l' intéressante question du vote municipal des femmes.\n", + "--- Result 3 ---\n", + "Le 20 juillet 1889, au Congrès socialiste intermfci mal de Paris, il proposa la résolution suivante : « Il sera organisé une grande manifestation internationale à dr.\n", + "--- Result 4 ---\n", + "Le congrès socialiste de 19 10 a réservé la question de principe, mais il avait stipulé que conformément aux résolutions des congrès internationaux de Paris et d’ Amsterdam, il n’ admettait pas comme possible la participation individuelle de certains socialistes, sans l’ assentiment du parti ouvrier, à un ministère quelconque ; le congrès de 1910 avait décidé, pour le surplus, que la question de la participation gouvernementale est « une question de tactique, et non de principe », qui devra être tranchée par un congrès spécial.\n", + "--- Result 5 ---\n", + "A l' un des derniers congrès de radiologie, tenu à Bruxelles en septembre 1910.\n" + ] + } + ], + "source": [ + "for i, d in enumerate(docs, 1):\n", + " print(f\"--- Result {i} ---\")\n", + " print(d.get(\"content_txt_fr\", \"[No text]\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "id": "73fafa3f-9b12-491c-9f8a-c56736c48bd6", + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "{'id': 'indeplux-1912-06-14-a-i0001-s-27',\n", + " 'type_s': 's',\n", + " 'content_txt_fr': 'Mais c’ est une question qui ne peut se régler en congrès internationaux et c’ est pourquoi le pays cjui ne présente pas une natalité suffisante sera étranglé, ce qui ne sera d’ ailleurs qu’ une avance sur son sui- cide.',\n", + " 'ci_id_s': 'indeplux-1912-06-14-a-i0001',\n", + " 'gte_multi_v768': [-0.081427164,\n", + " 0.064372316,\n", + " -0.045108054,\n", + " 0.08742539,\n", + " -0.016204905,\n", + " -0.0032661548,\n", + " -0.08083391,\n", + " -0.030488549,\n", + " 0.01922982,\n", + " -0.066497795,\n", + " 0.04242271,\n", + " -0.036173802,\n", + " -0.0028986486,\n", + " 0.034270063,\n", + " -0.03690813,\n", + " 0.09999781,\n", + " 0.025211757,\n", + " -0.004169398,\n", + " 0.04152064,\n", + " 0.032867514,\n", + " 0.11520032,\n", + " 0.09198125,\n", + " 0.005486816,\n", + " 0.015264476,\n", + " 0.017409217,\n", + " -0.005969191,\n", + " 0.10060896,\n", + " -0.066738024,\n", + " -0.051272426,\n", + " 0.038004458,\n", + " -0.10215557,\n", + " -0.016743958,\n", + " 0.017888524,\n", + " -0.00096381706,\n", + " 0.052417602,\n", + " -0.073400766,\n", + " 0.047756754,\n", + " -0.018304978,\n", + " -0.03343914,\n", + " 0.015744846,\n", + " -0.035610653,\n", + " 0.01637089,\n", + " -0.051607937,\n", + " 0.0026041695,\n", + " -0.012169081,\n", + " 0.037903298,\n", + " -0.06327127,\n", + " -0.043894477,\n", + " -0.05351843,\n", + " 0.044884857,\n", + " 0.06338861,\n", + " 0.022319878,\n", + " 0.011649567,\n", + " -0.0054243333,\n", + " 0.026314184,\n", + " 0.027909214,\n", + " -0.09507064,\n", + " 0.061315954,\n", + " 0.07815464,\n", + " -0.014403484,\n", + " 0.031844497,\n", + " -0.0021377155,\n", + " 0.0064931754,\n", + " -0.025778398,\n", + " -0.0113039855,\n", + " 0.013106857,\n", + " 0.027689118,\n", + " -0.011624109,\n", + " 0.081417605,\n", + " 0.044308018,\n", + " -0.0781789,\n", + " 0.033899177,\n", + " 0.0021870101,\n", + " -0.019256592,\n", + " -0.011104092,\n", + " 0.03836033,\n", + " -0.019176582,\n", + " -0.0010315784,\n", + " -0.0137142325,\n", + " 0.013355355,\n", + " -0.013917252,\n", + " -0.02555351,\n", + " -0.016202243,\n", + " 0.018706385,\n", + " -0.050871357,\n", + " -0.0070682834,\n", + " 0.060611002,\n", + " 0.042384453,\n", + " 0.016053265,\n", + " 0.08681886,\n", + " -0.010137089,\n", + " 0.05954166,\n", + " -0.06806551,\n", + " -0.0068755522,\n", + " 0.019395446,\n", + " 0.059344202,\n", + " -0.016546328,\n", + " 0.019943053,\n", + " 0.049762107,\n", + " 0.048172187,\n", + " 0.0039899475,\n", + " -0.035056632,\n", + " 0.030599825,\n", + " -0.04716478,\n", + " 0.051026646,\n", + " -0.02126569,\n", + " 0.0044269883,\n", + " 0.0019362805,\n", + " -0.032534923,\n", + " -0.04946502,\n", + " 0.009440294,\n", + " 0.035840407,\n", + " -0.09611488,\n", + " -0.053630944,\n", + " -0.04836141,\n", + " -0.0097440295,\n", + " 0.057466105,\n", + " -0.0057519134,\n", + " 0.022386527,\n", + " 0.03149422,\n", + " -0.02305837,\n", + " -0.08078451,\n", + " -0.016198197,\n", + " 0.0053822338,\n", + " -0.08808732,\n", + " -0.023794789,\n", + " -0.024558565,\n", + " -0.057138834,\n", + " 0.052244026,\n", + " -0.007293488,\n", + " 0.1049111,\n", + " -0.0022571476,\n", + " -0.036102846,\n", + " -0.07726404,\n", + " -0.018246813,\n", + " -0.033013213,\n", + " -0.02333869,\n", + " 0.02077296,\n", + " 0.021713099,\n", + " -0.005465568,\n", + " -0.049857978,\n", + " 0.04799644,\n", + " -0.078355074,\n", + " 0.0021522,\n", + " -0.018461157,\n", + " 0.048754416,\n", + " -0.015175688,\n", + " -0.05485527,\n", + " 0.07835993,\n", + " 0.014683075,\n", + " -0.02412262,\n", + " 0.019611157,\n", + " 0.036663566,\n", + " 0.016612547,\n", + " 0.020707905,\n", + " -0.02157017,\n", + " -0.036986988,\n", + " 0.026372425,\n", + " -0.026306372,\n", + " -0.034135945,\n", + " 0.060493767,\n", + " 0.062349096,\n", + " 0.07548558,\n", + " -0.036325864,\n", + " -0.02152598,\n", + " 0.028488595,\n", + " 0.030044494,\n", + " 0.01852276,\n", + " 0.07674158,\n", + " -0.022839885,\n", + " -0.016950281,\n", + " 0.013122193,\n", + " 0.008219237,\n", + " -0.021939674,\n", + " -0.022592088,\n", + " -0.038033124,\n", + " 0.010979446,\n", + " 0.041204028,\n", + " -0.059076462,\n", + " 0.0033598582,\n", + " 0.02089602,\n", + " -0.059369985,\n", + " 0.0047558607,\n", + " -0.07706344,\n", + " 0.06355889,\n", + " 0.023710249,\n", + " -0.0041700536,\n", + " -0.07260834,\n", + " -0.035566736,\n", + " 0.038878743,\n", + " -0.019827707,\n", + " -0.036263216,\n", + " -0.063814625,\n", + " 0.017230544,\n", + " -0.0013633954,\n", + " -0.03908598,\n", + " 0.01250506,\n", + " 0.014394701,\n", + " 0.0041739405,\n", + " 0.0839863,\n", + " 0.0008519452,\n", + " 0.0104959095,\n", + " -0.013036082,\n", + " 0.015746057,\n", + " -0.05459077,\n", + " -0.052719757,\n", + " 0.0042646425,\n", + " 0.02956065,\n", + " 0.016120858,\n", + " -0.004233317,\n", + " 0.019077541,\n", + " -0.008454137,\n", + " 0.01175525,\n", + " -0.020472161,\n", + " -0.017467216,\n", + " -0.011110074,\n", + " -0.046194915,\n", + " -0.021829005,\n", + " 0.0131904315,\n", + " -0.002183448,\n", + " -0.0181923,\n", + " -0.01671806,\n", + " -0.03275726,\n", + " -0.0055113467,\n", + " 0.007338492,\n", + " 0.020452762,\n", + " -0.014988394,\n", + " 0.022865575,\n", + " -0.023398457,\n", + " 0.0048595606,\n", + " -0.011326758,\n", + " -0.0036041506,\n", + " 0.07581927,\n", + " 0.01818148,\n", + " -0.0033784837,\n", + " 0.021420475,\n", + " 0.039218593,\n", + " -0.02480191,\n", + " -0.021848006,\n", + " 0.041838992,\n", + " 0.011506943,\n", + " -0.012104254,\n", + " 0.001537347,\n", + " 0.03289704,\n", + " -0.061239846,\n", + " 0.038928296,\n", + " -0.012385192,\n", + " -0.032024134,\n", + " -0.013293794,\n", + " 0.015824921,\n", + " -0.009817402,\n", + " 0.031834833,\n", + " -0.0042468007,\n", + " 0.04379205,\n", + " -0.010797119,\n", + " -0.037814178,\n", + " -0.018777076,\n", + " 0.022162588,\n", + " 0.050620783,\n", + " -0.014713437,\n", + " -0.056102164,\n", + " -0.040111884,\n", + " -0.016369846,\n", + " -0.048014887,\n", + " 0.011927905,\n", + " -0.08738478,\n", + " 0.049479567,\n", + " 0.002872294,\n", + " 0.018098652,\n", + " -0.026732583,\n", + " -0.019144585,\n", + " 0.013347716,\n", + " -0.012236467,\n", + " 0.039242662,\n", + " 0.020409267,\n", + " 0.026534997,\n", + " 0.021626161,\n", + " -0.049137626,\n", + " 0.057768505,\n", + " 0.024537649,\n", + " 0.040146396,\n", + " -0.030630916,\n", + " -0.012266775,\n", + " 0.008592031,\n", + " -0.06309963,\n", + " 0.058924045,\n", + " 0.027965445,\n", + " -0.0066002603,\n", + " -0.060511287,\n", + " 0.02022797,\n", + " 0.022165498,\n", + " -0.043309417,\n", + " -0.00970387,\n", + " 0.03280196,\n", + " 0.05165125,\n", + " -0.027301418,\n", + " -0.024620913,\n", + " 0.034908008,\n", + " 0.030793473,\n", + " 0.0042416714,\n", + " -0.016695043,\n", + " -0.016573505,\n", + " 0.0034687242,\n", + " 0.009735219,\n", + " -0.04334127,\n", + " -0.0051383646,\n", + " -0.0029800101,\n", + " -0.03669362,\n", + " -0.013573973,\n", + " 0.02915002,\n", + " 0.053568836,\n", + " 0.013559603,\n", + " -0.0056021395,\n", + " -0.083493836,\n", + " 0.048657723,\n", + " -0.024513677,\n", + " 0.011142334,\n", + " 0.024816891,\n", + " -0.016300842,\n", + " -0.033580966,\n", + " 0.02569195,\n", + " 0.009701036,\n", + " -0.051402524,\n", + " 0.04622702,\n", + " -0.028156225,\n", + " -0.022232272,\n", + " -0.015802791,\n", + " 0.0014903932,\n", + " -0.040654257,\n", + " 0.0014043513,\n", + " 0.034458928,\n", + " 0.034616753,\n", + " 0.022009227,\n", + " -0.053867683,\n", + " 0.025601747,\n", + " 0.08592088,\n", + " 0.031311963,\n", + " 0.0006002426,\n", + " 0.02619659,\n", + " 0.004906178,\n", + " -0.0008670905,\n", + " 0.037017092,\n", + " -0.06659331,\n", + " 0.054778777,\n", + " -0.018856762,\n", + " -0.013714602,\n", + " -0.0010605609,\n", + " 0.03824293,\n", + " 0.03665221,\n", + " 0.021349635,\n", + " -0.007914992,\n", + " 0.02346739,\n", + " 0.05344404,\n", + " -0.0035946732,\n", + " -0.007898519,\n", + " 0.003189902,\n", + " 0.017389607,\n", + " 0.059460696,\n", + " -0.018158963,\n", + " 0.06321497,\n", + " 0.057064842,\n", + " -0.045017887,\n", + " 0.00028358883,\n", + " 0.02802503,\n", + " 0.025817374,\n", + " -0.05629147,\n", + " -0.04575568,\n", + " 0.0026548724,\n", + " 0.05056999,\n", + " 0.019218508,\n", + " 0.0021371325,\n", + " 0.021273365,\n", + " 0.02881533,\n", + " 0.07721803,\n", + " -0.045122124,\n", + " 0.046677075,\n", + " -0.034335572,\n", + " 0.037475634,\n", + " 0.018491682,\n", + " 0.0051161293,\n", + " 0.019452339,\n", + " 0.028822228,\n", + " 0.109846845,\n", + " -0.013732984,\n", + " 0.014720311,\n", + " 0.0011648148,\n", + " -0.002483864,\n", + " -0.041083615,\n", + " -0.021729276,\n", + " -0.031135181,\n", + " -0.012765439,\n", + " -0.034220085,\n", + " -0.025189184,\n", + " 0.017646268,\n", + " 0.023410823,\n", + " 0.012667995,\n", + " 0.053882256,\n", + " 0.050381634,\n", + " -0.04154851,\n", + " -0.025424054,\n", + " 0.056466915,\n", + " 0.014838826,\n", + " 0.004047925,\n", + " -0.010193228,\n", + " 0.030313522,\n", + " -0.012074564,\n", + " 0.01720908,\n", + " 0.01081676,\n", + " 0.042463094,\n", + " 0.029379077,\n", + " 0.051904935,\n", + " -0.0089294,\n", + " 0.0012408567,\n", + " -0.03142283,\n", + " -0.0015596739,\n", + " 0.03380737,\n", + " 0.019032702,\n", + " 0.021951968,\n", + " 0.11533221,\n", + " -0.007856628,\n", + " 0.02281904,\n", + " 0.00881275,\n", + " 0.020597987,\n", + " -0.02549735,\n", + " -0.030028533,\n", + " -0.06013915,\n", + " 0.0031522315,\n", + " 0.017439466,\n", + " 0.04207593,\n", + " 0.091469854,\n", + " -0.015765613,\n", + " 0.0149031235,\n", + " -0.01956561,\n", + " -0.002414244,\n", + " -0.1094421,\n", + " 0.005633813,\n", + " -0.0033078243,\n", + " -0.046207964,\n", + " 0.0033252954,\n", + " 0.01700336,\n", + " -0.064000346,\n", + " 0.013695957,\n", + " 0.018813917,\n", + " -0.019596778,\n", + " -0.018768733,\n", + " -0.062085226,\n", + " -0.04393183,\n", + " 0.01740412,\n", + " 0.0068095806,\n", + " 0.02982634,\n", + " -0.031117061,\n", + " 0.0010879937,\n", + " -0.030221133,\n", + " -0.02305694,\n", + " 0.012205767,\n", + " 0.020197889,\n", + " -0.011025782,\n", + " -0.011664094,\n", + " -0.0087072505,\n", + " -0.030868791,\n", + " -0.0022526246,\n", + " 0.009358584,\n", + " -0.036634415,\n", + " 0.026896648,\n", + " 0.05941364,\n", + " 0.019537749,\n", + " -0.01794697,\n", + " 0.038881943,\n", + " 0.06502216,\n", + " 0.022962114,\n", + " 0.03018654,\n", + " 0.026737124,\n", + " 0.019744167,\n", + " -0.026662428,\n", + " 0.012199454,\n", + " -0.008034174,\n", + " 0.0067995223,\n", + " 0.023114827,\n", + " 0.017662069,\n", + " -0.0037633989,\n", + " -0.020161726,\n", + " 0.01888501,\n", + " -0.032249585,\n", + " -0.030862305,\n", + " -0.03098063,\n", + " 0.014843968,\n", + " 0.022338323,\n", + " -0.08554132,\n", + " 0.032697104,\n", + " 0.0766141,\n", + " 0.06331765,\n", + " 0.0063295616,\n", + " -0.046704944,\n", + " -0.015937336,\n", + " 0.0146816345,\n", + " 0.024641693,\n", + " 0.022917889,\n", + " -0.047505036,\n", + " 0.0017036259,\n", + " 0.05883194,\n", + " -0.013983027,\n", + " -0.007955594,\n", + " -0.059356853,\n", + " 0.010960551,\n", + " 0.03761545,\n", + " 0.004573043,\n", + " 0.053301178,\n", + " -0.030775413,\n", + " 0.013350438,\n", + " 0.02404047,\n", + " -0.069119535,\n", + " 0.027269974,\n", + " 0.0013833656,\n", + " -0.058948528,\n", + " 0.016748793,\n", + " -0.022794815,\n", + " -0.024996081,\n", + " 0.03278682,\n", + " -0.015970118,\n", + " 0.0064338837,\n", + " 0.025020966,\n", + " -0.025259184,\n", + " -0.07177622,\n", + " 0.019871945,\n", + " -0.05269971,\n", + " 0.017440531,\n", + " 0.0117028095,\n", + " -0.006656424,\n", + " -0.010291318,\n", + " -0.017315334,\n", + " -0.007990969,\n", + " 0.086795285,\n", + " 0.020211952,\n", + " 0.009114601,\n", + " 0.059573226,\n", + " 0.040704682,\n", + " 0.025457015,\n", + " -0.031309012,\n", + " 0.0058753267,\n", + " 0.04901623,\n", + " -0.0122652855,\n", + " -0.018044721,\n", + " -0.007143741,\n", + " 0.002831681,\n", + " -0.012250971,\n", + " -0.026678441,\n", + " 0.032056082,\n", + " -0.030600509,\n", + " -0.04300202,\n", + " -0.031419076,\n", + " 0.04335907,\n", + " 0.05062743,\n", + " 0.06994422,\n", + " -0.0031660371,\n", + " -0.070930205,\n", + " -0.03823314,\n", + " 0.0006152355,\n", + " 0.009303026,\n", + " -0.008590888,\n", + " -0.01509825,\n", + " -0.022812745,\n", + " -0.08762697,\n", + " 0.051922265,\n", + " 0.04894216,\n", + " 0.0057275896,\n", + " -0.0015417227,\n", + " -0.013337219,\n", + " -0.04094926,\n", + " 0.02615881,\n", + " 0.015957305,\n", + " -0.008662798,\n", + " 0.022658108,\n", + " -0.004368052,\n", + " -0.06387781,\n", + " -0.00049686554,\n", + " -0.010450126,\n", + " -0.010210296,\n", + " 0.031181276,\n", + " -0.027020259,\n", + " 0.021817883,\n", + " -0.020034732,\n", + " 0.06912386,\n", + " -0.009485199,\n", + " -0.017461605,\n", + " -0.036170892,\n", + " 0.015329548,\n", + " 0.0062945304,\n", + " 0.045467105,\n", + " -0.044223413,\n", + " -0.004715235,\n", + " -0.033207588,\n", + " -0.0058536036,\n", + " 0.0050861333,\n", + " -0.06395814,\n", + " -0.004318634,\n", + " 0.024803467,\n", + " 0.008540717,\n", + " 0.02915922,\n", + " 0.059703548,\n", + " 0.02672467,\n", + " 0.013200832,\n", + " -0.027720576,\n", + " 0.00977768,\n", + " -0.038109757,\n", + " -0.03530302,\n", + " 0.033653025,\n", + " 0.026344186,\n", + " -0.07872108,\n", + " -0.03482698,\n", + " -0.029127572,\n", + " -0.0055903303,\n", + " -0.007942379,\n", + " 0.002264677,\n", + " 0.03818393,\n", + " -0.04583064,\n", + " 0.018037342,\n", + " -0.085961446,\n", + " -0.039332535,\n", + " -9.797573e-05,\n", + " 0.022565985,\n", + " -0.02423783,\n", + " 0.0027169255,\n", + " 0.041872244,\n", + " -0.03147955,\n", + " 0.02825741,\n", + " -0.008287027,\n", + " -0.04118363,\n", + " 0.029515438,\n", + " -0.039799336,\n", + " -0.0266588,\n", + " 0.02826509,\n", + " -0.02063068,\n", + " -0.006316049,\n", + " 0.017246423,\n", + " 0.034976125,\n", + " 0.0076519162,\n", + " -0.030508237,\n", + " 0.0037944815,\n", + " 0.027766814,\n", + " -0.08801824,\n", + " 0.008386495,\n", + " 0.010155254,\n", + " 0.047535814,\n", + " 0.0467276,\n", + " -0.012654169,\n", + " -0.023404893,\n", + " 0.009156073,\n", + " -0.021613082,\n", + " -0.022608759,\n", + " 0.0040091854,\n", + " 0.027937712,\n", + " 0.0017836906,\n", + " -0.029016731,\n", + " -0.014328147,\n", + " -0.013694352,\n", + " 0.01624316,\n", + " -0.087653704,\n", + " -0.007499973,\n", + " 0.0014776542,\n", + " 0.023297846,\n", + " 0.017909396,\n", + " 0.026473945,\n", + " 0.049817335,\n", + " -0.004742915,\n", + " -0.045145947,\n", + " -0.005817356,\n", + " 0.0093169315,\n", + " -0.0024441234,\n", + " -0.020449957,\n", + " -0.057113476,\n", + " -0.00037673535,\n", + " -0.0068436866,\n", + " 0.049108807,\n", + " -0.004650932,\n", + " -0.03991428,\n", + " 0.041935865,\n", + " -0.0046782154,\n", + " -0.006373373,\n", + " -0.02583609,\n", + " 0.010704986,\n", + " 0.020917885,\n", + " -0.03886426,\n", + " -0.022924274,\n", + " 0.026235584,\n", + " -0.016595159,\n", + " 0.0064262864,\n", + " -0.006728229,\n", + " 0.04023094,\n", + " 0.018823523,\n", + " -0.021455951,\n", + " -0.034144104,\n", + " 0.007861527,\n", + " -0.00029349345,\n", + " -0.008764708,\n", + " 0.02014379,\n", + " -0.0150536,\n", + " 0.04630012,\n", + " 0.046140317,\n", + " 0.020522414,\n", + " 0.012370299,\n", + " 0.026588684,\n", + " 0.0010963973,\n", + " 0.047540367,\n", + " -0.030359069,\n", + " -0.013518566,\n", + " -0.022742666,\n", + " -0.0046805856,\n", + " 0.014406342,\n", + " -0.007278617,\n", + " -0.012485435,\n", + " 0.04940796,\n", + " -0.04546034,\n", + " -0.020017812,\n", + " 0.02772044,\n", + " -0.005244903,\n", + " -0.03883373,\n", + " -0.0093254745,\n", + " 0.02377589,\n", + " -0.058478873,\n", + " 0.026416734,\n", + " 0.020168163,\n", + " -0.010474008,\n", + " -0.012232645,\n", + " -0.0027875488,\n", + " 0.0048259352,\n", + " -0.03345372,\n", + " 0.023432989,\n", + " 0.0073413025,\n", + " -0.004630064,\n", + " -0.016431082,\n", + " -0.010867781,\n", + " 0.046610504,\n", + " 0.02221005,\n", + " -0.035439335,\n", + " 0.021267762,\n", + " 0.003914809,\n", + " 0.0372266,\n", + " -0.05508867,\n", + " 0.0026225722,\n", + " -0.020968309,\n", + " 0.0037491478,\n", + " -0.015431687,\n", + " 0.069426954,\n", + " 0.006881036,\n", + " -0.0059120427,\n", + " 0.023701912,\n", + " -0.023184957,\n", + " 0.018712236,\n", + " 0.006075447,\n", + " 0.032562926,\n", + " -0.023184566,\n", + " 0.014065631,\n", + " 0.0150226895,\n", + " -0.002041589,\n", + " -0.0266023,\n", + " -0.0013457921,\n", + " 0.004231847,\n", + " -0.052936506,\n", + " -0.0733579,\n", + " 0.02305891,\n", + " 0.0118407635,\n", + " 0.026815364,\n", + " 0.03814409,\n", + " 0.008659009,\n", + " -0.017255636,\n", + " 0.02480575,\n", + " -0.0037373884,\n", + " 0.039746176],\n", + " 'lg_s': 'fr',\n", + " '_version_': 1843522628974804992,\n", + " '_root_': 'indeplux-1912-06-14-a-i0001-s-27'}" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "docs[0]" ] }, { "cell_type": "code", - "execution_count": 26, - "id": "43a93d9a", + "execution_count": 37, + "id": "ca0d7ea8-7545-449a-aad3-e95d2ea33fb2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "'La peau du chat est.'" + "'Mais c’ est une question qui ne peut se régler en congrès internationaux et c’ est pourquoi le pays cjui ne présente pas une natalité suffisante sera étranglé, ce qui ne sera d’ ailleurs qu’ une avanc'" ] }, - "execution_count": 26, + "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "doc = result['solrResponse']['response']['docs'][0]\n", - "doc['content_txt_fr'][:200] # first 200 characters of the document content" + "docs[0]['content_txt_fr'][:200] # first 200 characters of the document content" + ] + }, + { + "cell_type": "markdown", + "id": "54991815-d7d6-4436-82eb-d1948a35aaf8", + "metadata": {}, + "source": [ + "Let's take the first returned document's embedding." ] }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 38, + "id": "0b4d2ef2-bfc1-4941-aba4-ec6ab7002310", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[-0.081427164, 0.064372316, -0.045108054]" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "embedding = docs[0]['gte_multi_v768']\n", + "\n", + "embedding[:3]" + ] + }, + { + "cell_type": "code", + "execution_count": 39, "id": "f85b2817", "metadata": {}, "outputs": [], @@ -168,7 +1082,7 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 75, "id": "b97665a0", "metadata": {}, "outputs": [ @@ -176,29 +1090,2380 @@ "name": "stdout", "output_type": "stream", "text": [ - "Got 3 solr documents\n" + "✅ Got 3 Solr document(s)\n", + "\n" ] } ], "source": [ "result = impresso.experiments.execute(\n", - " experiment_id=\"subdoc-embeddings\",\n", - " body={\n", - " \"solrPayload\": {\n", - " \"query\": \"{!knn f=gte_multi_v768 topK=3}\" + str(embedding),\n", - " \"limit\": 3,\n", - " \"params\": {\n", - " \"hl\": False\n", - " }\n", + " experiment_id=\"subdoc-embeddings\",\n", + " body={\n", + " \"solrPayload\": {\n", + " \"query\": \"{!knn f=gte_multi_v768 topK=3}\" + str(embedding),\n", + " \"limit\": 3,\n", + " \"params\": {\n", + " \"fq\": \"type_s:s\", # type_s:s restricts search to sentences (s=sentence)\n", + " # \"fl\": \"id,score,content_txt_fr,ci_id_s\", -- add these later if you want to return only specific fields\n", + " # for now let's return everything\n", + " \"hl\": False\n", + " }\n", + " }\n", " }\n", - " }\n", ")\n", - "print(f\"Got {len(result['solrResponse']['response']['docs'])} solr documents\")" + "\n", + "docs = result[\"solrResponse\"][\"response\"][\"docs\"]\n", + "print(f\"✅ Got {len(docs)} Solr document(s)\\n\")" ] }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 76, + "id": "09ec22e2-8605-47fe-ae74-10371ffb8453", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[{'id': 'GDL-1912-01-25-a-i0001-s-65',\n", + " 'type_s': 's',\n", + " 'content_txt_fr': \"En outre, la nouvelle convention accorde la franchise de port pour la correspondance drdniaire des institutions nationales ayant un caractère scientifique et d' intérêt général ; ainsi qu' aux congrès scientifiques sud-américains composés de la majorité des pays de ce continent.\",\n", + " 'ci_id_s': 'GDL-1912-01-25-a-i0001',\n", + " 'gte_multi_v768': [-0.051615752,\n", + " 0.05201664,\n", + " -0.049590472,\n", + " 0.03735869,\n", + " -0.05054572,\n", + " 0.0066682235,\n", + " 0.017149948,\n", + " 0.029176751,\n", + " 0.1008355,\n", + " -0.06555545,\n", + " 0.02282818,\n", + " -0.004284408,\n", + " 0.06918294,\n", + " 0.05266427,\n", + " -0.1323649,\n", + " 0.07952411,\n", + " 0.10921394,\n", + " 0.061787345,\n", + " 0.026983595,\n", + " -0.03820048,\n", + " 0.06531311,\n", + " 0.04358564,\n", + " -0.022574957,\n", + " -0.055607993,\n", + " -0.017880114,\n", + " 0.08863045,\n", + " 0.075027466,\n", + " 0.00598791,\n", + " -0.029623808,\n", + " 0.04483322,\n", + " -0.07739359,\n", + " 0.013161964,\n", + " 0.06096676,\n", + " 0.07653891,\n", + " 0.020618537,\n", + " 0.066804744,\n", + " 0.003295666,\n", + " 0.018790608,\n", + " -0.019829411,\n", + " 0.063828565,\n", + " -0.009492278,\n", + " 0.012099424,\n", + " -0.03702587,\n", + " 0.06130341,\n", + " -0.044647235,\n", + " 0.064631134,\n", + " -0.042960476,\n", + " 0.031465385,\n", + " 0.016465947,\n", + " 0.0739859,\n", + " -0.029774092,\n", + " 0.0396995,\n", + " 0.0077195545,\n", + " 0.0735613,\n", + " 0.016696824,\n", + " 0.05187279,\n", + " -0.03604686,\n", + " 0.03519577,\n", + " 0.08680929,\n", + " -0.018466,\n", + " 0.06026104,\n", + " -0.0032086065,\n", + " -0.008187865,\n", + " 0.037388857,\n", + " 0.06477858,\n", + " -0.04534802,\n", + " 0.015970873,\n", + " -0.043672122,\n", + " 0.051750317,\n", + " -0.000932299,\n", + " -0.072477564,\n", + " 0.024720566,\n", + " 0.022310376,\n", + " 0.014357782,\n", + " -0.049257237,\n", + " 0.076934956,\n", + " -0.0076242355,\n", + " 0.008307401,\n", + " -0.010138375,\n", + " 0.037909407,\n", + " 0.0040230146,\n", + " -0.048211735,\n", + " -0.00052228814,\n", + " -0.024161067,\n", + " -0.016096635,\n", + " 0.0059468257,\n", + " -0.013075567,\n", + " 0.02069194,\n", + " 0.008249857,\n", + " 0.017511917,\n", + " 0.11059983,\n", + " 0.07871855,\n", + " -0.035136413,\n", + " -0.0054236567,\n", + " 0.028771387,\n", + " 0.036885332,\n", + " -0.042637754,\n", + " -0.009461706,\n", + " 0.04435888,\n", + " 0.017993977,\n", + " -0.03013215,\n", + " 0.032274075,\n", + " 0.035419617,\n", + " -0.06720839,\n", + " 0.0127287125,\n", + " 0.021468151,\n", + " 0.01510161,\n", + " 0.01637483,\n", + " -0.020533161,\n", + " -0.015646867,\n", + " -0.008983932,\n", + " -0.021627953,\n", + " -0.051015522,\n", + " 0.011945374,\n", + " -0.025561973,\n", + " 0.009892356,\n", + " 0.036670934,\n", + " -0.010536299,\n", + " 0.06747981,\n", + " 0.070237994,\n", + " -0.014428563,\n", + " 5.314551e-05,\n", + " -0.0674437,\n", + " 0.0013509023,\n", + " -0.119708546,\n", + " 0.035609808,\n", + " 0.023638168,\n", + " -0.046389047,\n", + " -0.0034867222,\n", + " -0.029822085,\n", + " 0.07264101,\n", + " -0.01248558,\n", + " -0.028398713,\n", + " -0.0034294068,\n", + " 0.0460668,\n", + " -0.043848146,\n", + " -0.011794878,\n", + " 0.021345017,\n", + " 0.0004661887,\n", + " 0.0034974788,\n", + " -0.03950107,\n", + " 0.0319008,\n", + " -0.03189924,\n", + " 0.051244847,\n", + " 0.0053909104,\n", + " -0.0077845873,\n", + " 0.037087847,\n", + " -0.07880855,\n", + " 0.024216598,\n", + " -0.020771429,\n", + " -0.0034421848,\n", + " 0.03145833,\n", + " -0.03342526,\n", + " -0.0037502071,\n", + " 0.020279478,\n", + " -0.010619189,\n", + " 0.017508822,\n", + " 0.059134666,\n", + " -0.021911254,\n", + " -0.045016967,\n", + " 0.040860157,\n", + " 0.04547328,\n", + " -0.017553328,\n", + " -0.023265574,\n", + " -0.03242842,\n", + " -0.013684788,\n", + " -0.011217002,\n", + " 0.016167177,\n", + " 0.06555258,\n", + " 0.010355337,\n", + " -0.06031211,\n", + " 0.032271758,\n", + " 0.030278115,\n", + " -0.038748793,\n", + " -0.035640717,\n", + " 0.05087693,\n", + " -0.023270492,\n", + " 0.027843362,\n", + " -0.054154206,\n", + " 0.06533668,\n", + " 0.04797114,\n", + " -0.0014793635,\n", + " -0.084928125,\n", + " -0.083849825,\n", + " -0.0061715883,\n", + " -0.014985692,\n", + " 0.0099981455,\n", + " -0.020289913,\n", + " -0.029778289,\n", + " 0.02260849,\n", + " -0.034603857,\n", + " -0.045593247,\n", + " -0.06415319,\n", + " 0.01738982,\n", + " -0.037352238,\n", + " -0.040368818,\n", + " 0.010010408,\n", + " 0.02707113,\n", + " -0.011680812,\n", + " -0.018027654,\n", + " 0.024377994,\n", + " 0.023387276,\n", + " -0.016730819,\n", + " 0.03560658,\n", + " 0.035914868,\n", + " -0.026126612,\n", + " -0.0061368523,\n", + " -0.011479972,\n", + " 0.0100026075,\n", + " 0.010929561,\n", + " 0.02099457,\n", + " -0.01906599,\n", + " 0.034597356,\n", + " 0.018949876,\n", + " 0.02747244,\n", + " -0.022969738,\n", + " -0.04813395,\n", + " -0.018661518,\n", + " -0.013425553,\n", + " -0.01429428,\n", + " -0.016052166,\n", + " -0.0072409627,\n", + " -0.010831443,\n", + " -0.011443295,\n", + " -0.0062117577,\n", + " 0.010178804,\n", + " -0.025773551,\n", + " 0.0010628019,\n", + " 0.009158145,\n", + " 0.03361166,\n", + " -0.016050575,\n", + " -0.0063553024,\n", + " -0.021517018,\n", + " -0.018869486,\n", + " 0.0022371148,\n", + " 0.008782952,\n", + " 0.015057313,\n", + " 0.048567265,\n", + " 0.035071198,\n", + " 0.014853163,\n", + " 0.020440245,\n", + " -0.0015704749,\n", + " 0.030761616,\n", + " 0.043883644,\n", + " 0.021389458,\n", + " 0.078753635,\n", + " -0.05006035,\n", + " -0.03267201,\n", + " -0.032212876,\n", + " -0.0015862249,\n", + " -0.009999616,\n", + " 0.015572369,\n", + " 0.005264143,\n", + " 0.019296315,\n", + " -0.06321326,\n", + " -0.015364111,\n", + " -0.008891938,\n", + " 0.0379309,\n", + " 0.07026531,\n", + " -0.025643144,\n", + " -0.037246145,\n", + " 0.0011652529,\n", + " -0.0041922727,\n", + " -0.066680424,\n", + " 0.022525202,\n", + " -0.087653115,\n", + " -0.00046321764,\n", + " 0.035173774,\n", + " -0.058347158,\n", + " -0.045212146,\n", + " -0.017727235,\n", + " 0.05030683,\n", + " -0.022088924,\n", + " 0.012100173,\n", + " -0.03692086,\n", + " -0.028271051,\n", + " -0.04061667,\n", + " -0.0269407,\n", + " -0.002010739,\n", + " 0.029786596,\n", + " 0.05351522,\n", + " 0.0003377929,\n", + " -0.031983797,\n", + " 0.020290243,\n", + " -0.037977874,\n", + " 0.013784169,\n", + " 0.044094533,\n", + " -0.014481101,\n", + " -0.012275437,\n", + " 0.03201192,\n", + " -0.027549576,\n", + " -0.033356402,\n", + " 0.025171299,\n", + " -0.0014885762,\n", + " 0.03243893,\n", + " -0.032851167,\n", + " -0.06013589,\n", + " -0.030034231,\n", + " 0.032897018,\n", + " -0.020489698,\n", + " -0.047812004,\n", + " -0.00567419,\n", + " 0.05399784,\n", + " 0.019845333,\n", + " 0.0014612435,\n", + " -0.03538008,\n", + " -0.025331436,\n", + " -0.05707104,\n", + " -0.05330605,\n", + " 0.038766127,\n", + " 0.007857965,\n", + " -0.0053681857,\n", + " -0.03586249,\n", + " -0.01866089,\n", + " 0.01579822,\n", + " 0.03613172,\n", + " 0.037488427,\n", + " -0.019580815,\n", + " -0.07559065,\n", + " 0.00030233548,\n", + " 0.0071869846,\n", + " 0.042891856,\n", + " -0.011900373,\n", + " 0.019067554,\n", + " 0.008102365,\n", + " -0.036573064,\n", + " 0.03383329,\n", + " 0.006066424,\n", + " -0.016126228,\n", + " -0.0052911234,\n", + " 0.0048901057,\n", + " 0.01314156,\n", + " 0.025600754,\n", + " -0.074093334,\n", + " 0.027695276,\n", + " 0.006291198,\n", + " 0.02625118,\n", + " -0.020182537,\n", + " 0.042970575,\n", + " 0.015145495,\n", + " 0.050841894,\n", + " 0.029992417,\n", + " -0.037823357,\n", + " 0.02162169,\n", + " -0.0004975816,\n", + " 0.015324387,\n", + " 0.09757915,\n", + " 0.0071103387,\n", + " 0.026537541,\n", + " -0.02470101,\n", + " -0.008112973,\n", + " 0.065199085,\n", + " 0.024691427,\n", + " 0.012051806,\n", + " 0.01553574,\n", + " -0.00042199486,\n", + " -0.02054252,\n", + " 0.052470174,\n", + " -0.009581189,\n", + " 0.102331154,\n", + " 0.011244549,\n", + " -0.026529666,\n", + " 0.021703994,\n", + " 0.029255254,\n", + " -0.033522166,\n", + " -0.0033538584,\n", + " -0.0070442623,\n", + " -0.016324533,\n", + " 0.037732713,\n", + " -0.032576457,\n", + " -0.040807158,\n", + " -0.008757524,\n", + " -0.053028453,\n", + " 0.06443136,\n", + " -0.028360164,\n", + " 0.00793884,\n", + " 0.00080381194,\n", + " 0.016525649,\n", + " 0.011521507,\n", + " -0.037688028,\n", + " 0.014363011,\n", + " 0.048708167,\n", + " 0.023563437,\n", + " 0.019654522,\n", + " 0.026665622,\n", + " 0.024950488,\n", + " -0.01698889,\n", + " -0.029528854,\n", + " 0.0040981895,\n", + " -0.010146843,\n", + " 0.030675,\n", + " -0.029994393,\n", + " -0.009192765,\n", + " 0.03446682,\n", + " 0.034251526,\n", + " 0.03600614,\n", + " 0.0659266,\n", + " 0.020939728,\n", + " -0.001578855,\n", + " -0.031628225,\n", + " -0.010255595,\n", + " -0.018427707,\n", + " 0.023688035,\n", + " 0.03347112,\n", + " 0.028568842,\n", + " -0.017189782,\n", + " -0.00047363061,\n", + " -0.036223978,\n", + " -0.009172375,\n", + " -0.0018126044,\n", + " -0.007849988,\n", + " -0.0013811503,\n", + " 0.021117633,\n", + " -0.055400144,\n", + " 0.05436228,\n", + " -0.018043539,\n", + " 0.022044713,\n", + " 0.039080553,\n", + " 0.12751073,\n", + " -0.04444646,\n", + " 0.010775138,\n", + " 0.03844832,\n", + " -0.0030779832,\n", + " -0.042486113,\n", + " -0.019147042,\n", + " 0.016373958,\n", + " -0.015320426,\n", + " 0.06634088,\n", + " -0.0046683224,\n", + " 0.043384567,\n", + " -0.027876206,\n", + " 0.036001135,\n", + " -0.008584567,\n", + " -0.040407035,\n", + " -0.008925749,\n", + " 0.02888885,\n", + " 0.013540931,\n", + " 0.0050304076,\n", + " 0.02160886,\n", + " 0.04516263,\n", + " 0.009231834,\n", + " -0.033741664,\n", + " 0.00065888575,\n", + " -0.0710957,\n", + " 1.5987278e-05,\n", + " -0.0052919546,\n", + " -0.041170474,\n", + " 0.050878037,\n", + " -0.054500967,\n", + " 0.0232423,\n", + " -0.02436334,\n", + " 0.01782443,\n", + " -0.038947564,\n", + " -0.022209924,\n", + " 0.025447844,\n", + " 0.010800896,\n", + " -0.035247203,\n", + " 0.03191183,\n", + " 0.018120473,\n", + " -0.035099182,\n", + " 0.017186083,\n", + " -0.0054308176,\n", + " -0.02025944,\n", + " -0.043736085,\n", + " 0.044223715,\n", + " -0.0030811294,\n", + " 0.009738583,\n", + " 0.019276137,\n", + " -0.031711154,\n", + " 0.014869599,\n", + " -0.022863857,\n", + " 2.836195e-05,\n", + " -0.008967894,\n", + " 0.00046533902,\n", + " -0.0027317973,\n", + " 0.03320151,\n", + " 0.033403296,\n", + " 0.009921753,\n", + " 0.053694297,\n", + " 0.012582393,\n", + " 0.0022654077,\n", + " 0.016692635,\n", + " -0.004928809,\n", + " -0.024572613,\n", + " -0.041334826,\n", + " 0.013191648,\n", + " -0.045705587,\n", + " -0.071707435,\n", + " -0.0023595307,\n", + " 0.03667151,\n", + " 0.01801371,\n", + " 0.05604066,\n", + " 0.007484501,\n", + " -0.023895055,\n", + " 0.026544055,\n", + " 0.06848308,\n", + " -0.03402582,\n", + " -0.014590876,\n", + " 0.018667994,\n", + " -0.02413681,\n", + " -0.0557327,\n", + " -0.00880924,\n", + " 0.0075870627,\n", + " 0.045969486,\n", + " 0.0067385123,\n", + " -0.05023535,\n", + " 0.081836514,\n", + " -0.06026567,\n", + " 0.03204409,\n", + " -0.050728705,\n", + " -0.04784797,\n", + " -0.04638116,\n", + " -0.040952284,\n", + " -0.02447224,\n", + " -0.032183353,\n", + " -0.013256539,\n", + " 0.019123388,\n", + " -0.042831633,\n", + " -0.062628426,\n", + " 0.06995105,\n", + " 0.0218928,\n", + " -0.026224487,\n", + " -0.03296055,\n", + " 0.02423779,\n", + " 0.0125061,\n", + " -0.014371768,\n", + " -0.022743473,\n", + " -0.0012859623,\n", + " -0.0035610357,\n", + " -0.044091284,\n", + " 0.047810983,\n", + " 0.019562677,\n", + " 0.013388826,\n", + " -0.00012975158,\n", + " -0.05017465,\n", + " -0.004343915,\n", + " -0.020601902,\n", + " 0.025956646,\n", + " 0.023021614,\n", + " 0.009083039,\n", + " -0.064484395,\n", + " 0.021771988,\n", + " -0.017145673,\n", + " 0.036277615,\n", + " -0.008368489,\n", + " -0.0021986258,\n", + " 0.060611546,\n", + " -0.043499753,\n", + " -0.036393628,\n", + " 0.02459264,\n", + " 0.021183167,\n", + " 0.040052474,\n", + " 0.048911143,\n", + " 0.0018307558,\n", + " -0.0062714755,\n", + " -0.046554904,\n", + " 0.016214289,\n", + " -0.03842713,\n", + " 0.003178687,\n", + " 0.011152627,\n", + " -0.022851048,\n", + " -0.039629385,\n", + " 0.0016096554,\n", + " 0.041658763,\n", + " 0.05001978,\n", + " -0.029240588,\n", + " 0.002162648,\n", + " 0.032104794,\n", + " -0.00022503638,\n", + " 0.016997557,\n", + " -0.035969168,\n", + " -0.048558243,\n", + " 0.023870349,\n", + " -0.059834648,\n", + " -0.021206262,\n", + " -0.016442128,\n", + " -0.031565625,\n", + " -0.018789502,\n", + " -0.04246573,\n", + " 0.00845029,\n", + " 0.012945361,\n", + " -0.0007564261,\n", + " 0.005647039,\n", + " 0.051532418,\n", + " 0.012688975,\n", + " 0.0040408326,\n", + " -0.032260336,\n", + " 0.03656761,\n", + " -0.07194418,\n", + " -0.041979972,\n", + " 0.010066044,\n", + " -0.027413668,\n", + " 0.027000293,\n", + " -0.028258733,\n", + " 0.0447612,\n", + " 0.013929022,\n", + " -0.0039374125,\n", + " 0.011760333,\n", + " 0.017692896,\n", + " 0.026930073,\n", + " 0.008479024,\n", + " -0.02473566,\n", + " 0.008381769,\n", + " -0.025436137,\n", + " 0.026188018,\n", + " 0.029156292,\n", + " 0.023755766,\n", + " -0.07497574,\n", + " -0.016339287,\n", + " -0.0013905796,\n", + " -0.043203693,\n", + " -0.0062072696,\n", + " 0.031943817,\n", + " 0.022805497,\n", + " -0.079688415,\n", + " 0.009569476,\n", + " -0.041275863,\n", + " -0.051839773,\n", + " 0.02049438,\n", + " -0.03258229,\n", + " -0.02952811,\n", + " -0.040654197,\n", + " 0.0760365,\n", + " 0.003759511,\n", + " -0.007872424,\n", + " -0.0041186046,\n", + " -0.03549695,\n", + " -0.07696831,\n", + " -0.04416744,\n", + " -0.036314365,\n", + " -0.048074644,\n", + " -0.042366136,\n", + " -0.009535127,\n", + " -0.01230737,\n", + " -0.03673247,\n", + " 0.03096408,\n", + " -0.040810056,\n", + " 0.0038574976,\n", + " 0.02200458,\n", + " 0.002395138,\n", + " -0.030524805,\n", + " 0.009790649,\n", + " 0.009715365,\n", + " 0.04182122,\n", + " 0.030246397,\n", + " -0.03775568,\n", + " 0.007914768,\n", + " -0.009346499,\n", + " -0.03662862,\n", + " 0.014972676,\n", + " 0.03378411,\n", + " -0.048841577,\n", + " -0.0080238925,\n", + " -0.023907293,\n", + " -0.044986926,\n", + " -0.016466996,\n", + " -0.036266856,\n", + " -0.032230325,\n", + " -0.010940956,\n", + " 0.04471258,\n", + " 0.009344574,\n", + " -0.03611318,\n", + " 0.12816468,\n", + " 0.022074984,\n", + " -0.043523904,\n", + " 0.006402435,\n", + " 0.028247586,\n", + " 0.019084008,\n", + " 0.035987437,\n", + " 0.022977242,\n", + " 0.07773884,\n", + " -0.020035839,\n", + " -0.07158775,\n", + " -0.0010573787,\n", + " -0.02083184,\n", + " 0.03020219,\n", + " 0.026788305,\n", + " -0.043400384,\n", + " 0.026104674,\n", + " 0.00999582,\n", + " 0.01626253,\n", + " -0.053540748,\n", + " -0.028148673,\n", + " 0.02778322,\n", + " -0.07438462,\n", + " -0.0025628132,\n", + " -0.024457622,\n", + " 0.02585507,\n", + " 0.01657554,\n", + " 0.011961711,\n", + " 0.022417044,\n", + " -0.01039462,\n", + " 0.007850443,\n", + " -0.016122239,\n", + " 0.011302527,\n", + " -0.0024541456,\n", + " 0.010531964,\n", + " -0.0055627287,\n", + " 0.0050982395,\n", + " 0.01852299,\n", + " -0.0124726575,\n", + " -0.015639938,\n", + " 0.045438852,\n", + " 0.03466487,\n", + " 0.008506276,\n", + " 0.015463898,\n", + " -0.008730163,\n", + " -0.008596632,\n", + " 0.0006707985,\n", + " 0.024400542,\n", + " 0.04579195,\n", + " 0.0027356267,\n", + " -0.007052415,\n", + " 0.06489034,\n", + " -0.027781425,\n", + " -0.0048737847,\n", + " 0.0025846898,\n", + " -0.0011396497,\n", + " -0.061632667,\n", + " 0.053359985,\n", + " -0.053128414,\n", + " 0.0036842236,\n", + " -0.034069344,\n", + " 0.012609027,\n", + " 0.0021951955,\n", + " 0.007911464,\n", + " -0.027023457,\n", + " 0.070675686,\n", + " -0.030743489,\n", + " 0.024965337,\n", + " 0.040861886,\n", + " 0.015782895,\n", + " -0.03373192,\n", + " 0.0023073703,\n", + " 0.0075245793,\n", + " 0.009876064,\n", + " 0.019852692,\n", + " -0.03305989,\n", + " -0.00039043516,\n", + " 0.03612556,\n", + " 0.028484007,\n", + " -0.040667344,\n", + " -0.007624668,\n", + " 0.030401532,\n", + " 0.047515836,\n", + " 0.025457151,\n", + " 0.032370426,\n", + " -0.040960114,\n", + " 0.029548109,\n", + " -0.015358702,\n", + " -0.051161453,\n", + " 0.01867429,\n", + " -0.005633792,\n", + " -0.0164262,\n", + " 0.052699134,\n", + " -0.021055548,\n", + " 0.045519546,\n", + " -0.039158266,\n", + " -0.045086816,\n", + " 0.013899674,\n", + " 0.012462053,\n", + " 0.045320608,\n", + " -0.010657815,\n", + " 0.0069521023,\n", + " -0.032610457,\n", + " -0.05496854,\n", + " 0.019171735,\n", + " 0.06461833],\n", + " 'lg_s': 'fr',\n", + " '_version_': 1843523311144796160,\n", + " '_root_': 'GDL-1912-01-25-a-i0001-s-65'},\n", + " {'id': 'GDL-1912-01-25-a-i0001-s-29',\n", + " 'type_s': 's',\n", + " 'content_txt_fr': 'Certaines dispositions insérées dans la nouvelle convention sud-américaine ont sans contredit une portée autre que simplement postale.',\n", + " 'ci_id_s': 'GDL-1912-01-25-a-i0001',\n", + " 'gte_multi_v768': [-0.07270199,\n", + " 0.061392926,\n", + " -0.025212321,\n", + " 0.04842686,\n", + " -0.030294813,\n", + " 0.035191197,\n", + " -0.04358981,\n", + " 0.0038277104,\n", + " 0.085862525,\n", + " -0.04771203,\n", + " 0.01479704,\n", + " -0.013705449,\n", + " 0.027255017,\n", + " -0.00032638258,\n", + " -0.0535441,\n", + " 0.06433969,\n", + " 0.0870326,\n", + " 0.01321177,\n", + " 0.08558132,\n", + " 0.0005348483,\n", + " 0.08191568,\n", + " 0.025292994,\n", + " -0.039012924,\n", + " -0.020857098,\n", + " -0.0076694754,\n", + " 0.045723043,\n", + " 0.07569519,\n", + " -0.0071770684,\n", + " -0.07248518,\n", + " 0.016248405,\n", + " -0.09151575,\n", + " -0.028681815,\n", + " 0.0987924,\n", + " 0.011966113,\n", + " 0.056395438,\n", + " 0.011246147,\n", + " -0.032881655,\n", + " 0.016141465,\n", + " 0.03489068,\n", + " 0.015539575,\n", + " 0.048718866,\n", + " 0.05077653,\n", + " 0.0058326954,\n", + " -0.0015803308,\n", + " -0.016934639,\n", + " 0.031860374,\n", + " -0.039273117,\n", + " 0.050979868,\n", + " -0.012123115,\n", + " 0.029870547,\n", + " -0.044660818,\n", + " 0.010465813,\n", + " 0.020638926,\n", + " 0.008092918,\n", + " 0.03601937,\n", + " 0.032458056,\n", + " -0.105812624,\n", + " 0.014728648,\n", + " 0.07972083,\n", + " -0.0049583884,\n", + " 0.009220236,\n", + " -0.0022415437,\n", + " -0.05352581,\n", + " 0.03732541,\n", + " 0.06655571,\n", + " 0.020603223,\n", + " 0.033650473,\n", + " -0.047396556,\n", + " 0.07408663,\n", + " 0.005310279,\n", + " -0.051956754,\n", + " 0.004049972,\n", + " 0.0051678894,\n", + " 0.03096769,\n", + " -0.02968057,\n", + " 0.04748652,\n", + " -0.0059046075,\n", + " 0.03897846,\n", + " 0.031265296,\n", + " 0.010408316,\n", + " -0.05055094,\n", + " 0.0017630998,\n", + " 0.038844217,\n", + " -0.02534684,\n", + " -0.029771607,\n", + " -0.06687983,\n", + " -0.020020494,\n", + " 0.031773075,\n", + " 0.021087222,\n", + " -0.015565782,\n", + " 0.085392,\n", + " 0.064326406,\n", + " -0.018500494,\n", + " -0.006530731,\n", + " 0.047252536,\n", + " 0.0863165,\n", + " -0.035916302,\n", + " 0.023582164,\n", + " 0.08987791,\n", + " -0.017850174,\n", + " -0.075919226,\n", + " 0.038317222,\n", + " 0.020746242,\n", + " -0.054941483,\n", + " 0.032969326,\n", + " -0.02528709,\n", + " 0.02404556,\n", + " -0.018367948,\n", + " -0.044298112,\n", + " -0.032287084,\n", + " -0.042414498,\n", + " -0.05339762,\n", + " -0.06956395,\n", + " -0.028822873,\n", + " 0.0083979,\n", + " 0.023924638,\n", + " 0.028597783,\n", + " -0.06879725,\n", + " 0.048090484,\n", + " 0.059585776,\n", + " -0.016346283,\n", + " -0.005510254,\n", + " -0.064414516,\n", + " -0.024313008,\n", + " -0.053362753,\n", + " -0.001980558,\n", + " -0.0058990843,\n", + " -0.07435654,\n", + " 0.00804072,\n", + " 0.012742878,\n", + " 0.06795072,\n", + " 0.00017609757,\n", + " 0.046402264,\n", + " -0.01044538,\n", + " 0.0058663357,\n", + " -0.0451728,\n", + " 0.046612617,\n", + " 0.041145798,\n", + " 0.02295734,\n", + " -0.026006384,\n", + " -0.067377806,\n", + " -0.011408535,\n", + " -0.050212357,\n", + " 0.028501505,\n", + " 0.004271683,\n", + " 0.007336688,\n", + " -0.0026925632,\n", + " -0.07369538,\n", + " 0.05921478,\n", + " 0.008519318,\n", + " -0.005634117,\n", + " 0.029249141,\n", + " -0.022305908,\n", + " -0.017682286,\n", + " 0.024379397,\n", + " -0.04734149,\n", + " -0.015316724,\n", + " 0.075583965,\n", + " 0.010154082,\n", + " -0.03282173,\n", + " 0.029942155,\n", + " 0.038819402,\n", + " 0.02441589,\n", + " -0.01055037,\n", + " -0.05625257,\n", + " -0.014384699,\n", + " -0.024380013,\n", + " 0.03882333,\n", + " 0.07295608,\n", + " -0.013830722,\n", + " -0.060851064,\n", + " 0.017682424,\n", + " 0.020742288,\n", + " -0.027935466,\n", + " -0.027335946,\n", + " -0.03009823,\n", + " 0.0014494349,\n", + " 0.057282817,\n", + " -0.06258341,\n", + " 0.04828263,\n", + " -0.013397304,\n", + " 0.033821102,\n", + " -0.09812918,\n", + " -0.02750474,\n", + " 0.060738374,\n", + " 0.018970234,\n", + " 0.0059009683,\n", + " -0.0040276865,\n", + " 0.03282429,\n", + " -0.008775085,\n", + " -0.017078843,\n", + " -0.015721487,\n", + " -0.06266291,\n", + " 0.015922893,\n", + " 0.0022748741,\n", + " -0.020557612,\n", + " -0.012811559,\n", + " 0.045904584,\n", + " -0.034843687,\n", + " -0.030370345,\n", + " -0.0035589614,\n", + " 0.019647267,\n", + " 0.040806767,\n", + " 0.037716903,\n", + " 0.0047070934,\n", + " -0.051038835,\n", + " 0.0053223954,\n", + " -0.0051626465,\n", + " 0.004518503,\n", + " -0.009002026,\n", + " 0.015349202,\n", + " -0.037259646,\n", + " 0.03074719,\n", + " 0.027023815,\n", + " 0.010073604,\n", + " 0.015536163,\n", + " -0.055264518,\n", + " -0.018882325,\n", + " 0.004607553,\n", + " -0.009193998,\n", + " -0.011627999,\n", + " 0.004904914,\n", + " -0.014073629,\n", + " -0.02542841,\n", + " -0.04605124,\n", + " 0.021779291,\n", + " -0.01680755,\n", + " 0.021296147,\n", + " -0.015360311,\n", + " 0.009882392,\n", + " 0.030316025,\n", + " 0.024714394,\n", + " 0.009831074,\n", + " -0.04055002,\n", + " -0.01691468,\n", + " 0.027992884,\n", + " 0.0024250648,\n", + " 0.03726409,\n", + " -0.009548601,\n", + " 0.056431785,\n", + " 0.017792832,\n", + " -0.017150199,\n", + " 0.04523755,\n", + " 0.030130023,\n", + " -0.009212122,\n", + " 0.05134318,\n", + " 0.0040995083,\n", + " -0.064521655,\n", + " -0.04092778,\n", + " -0.019817367,\n", + " -0.0012400284,\n", + " 0.019691017,\n", + " 0.038562704,\n", + " 0.03977343,\n", + " -0.048494305,\n", + " -0.025027953,\n", + " -0.01927051,\n", + " -0.0015091224,\n", + " 0.0696117,\n", + " -0.0492665,\n", + " -0.014430027,\n", + " -0.01078952,\n", + " -0.046552517,\n", + " -0.045800272,\n", + " 0.0245287,\n", + " -0.10945937,\n", + " -0.010983787,\n", + " 0.03558626,\n", + " -0.029388275,\n", + " -0.04510395,\n", + " -0.025314933,\n", + " 0.10240726,\n", + " -0.05566458,\n", + " 0.0903111,\n", + " -0.03553116,\n", + " -0.0063938363,\n", + " -0.0601896,\n", + " -0.06805767,\n", + " 0.040524926,\n", + " 0.025733506,\n", + " -0.002730592,\n", + " -0.026106093,\n", + " -0.047036238,\n", + " -0.027412934,\n", + " -0.05640688,\n", + " 0.036764037,\n", + " 0.03826593,\n", + " -0.01328978,\n", + " -0.006152576,\n", + " 0.08365534,\n", + " 0.023071205,\n", + " 0.0014393347,\n", + " 0.0002518021,\n", + " 0.021357318,\n", + " 0.019425025,\n", + " -0.04351827,\n", + " -0.06667988,\n", + " 0.011600028,\n", + " 0.04470064,\n", + " -0.0285423,\n", + " -0.028581293,\n", + " -0.031258833,\n", + " 0.062057465,\n", + " 0.031595234,\n", + " -0.02372499,\n", + " -0.007897933,\n", + " -0.020015046,\n", + " -0.040688634,\n", + " -0.024159312,\n", + " 0.0125957085,\n", + " 0.012913835,\n", + " 0.015382748,\n", + " -0.029148549,\n", + " -0.041560646,\n", + " 0.026299838,\n", + " 0.02667616,\n", + " 0.05904669,\n", + " -0.009734496,\n", + " -0.082171634,\n", + " -0.04897272,\n", + " -0.047273252,\n", + " 0.022053381,\n", + " -0.0102919405,\n", + " 0.005035418,\n", + " -0.016853224,\n", + " -0.026692236,\n", + " 0.03900197,\n", + " 0.025118783,\n", + " -0.0038165401,\n", + " -0.018625524,\n", + " -0.00093953725,\n", + " 0.026513776,\n", + " 0.0202959,\n", + " -0.051877648,\n", + " 0.017134102,\n", + " 0.03131422,\n", + " 0.039644957,\n", + " -0.042753182,\n", + " 0.027404577,\n", + " 0.010539758,\n", + " 0.024265798,\n", + " 0.02560602,\n", + " -0.07568404,\n", + " 0.019028177,\n", + " 0.039411005,\n", + " -0.02820163,\n", + " 0.071243376,\n", + " -0.002909679,\n", + " 0.011384622,\n", + " -0.034663226,\n", + " -0.02491936,\n", + " 0.010973925,\n", + " 0.013038525,\n", + " -0.016868137,\n", + " 0.013330403,\n", + " 0.03721675,\n", + " -0.0116533525,\n", + " 0.0660362,\n", + " 0.013076732,\n", + " 0.037467334,\n", + " 0.0040909257,\n", + " -0.0125504825,\n", + " 0.00473948,\n", + " 0.009605131,\n", + " 2.7920505e-05,\n", + " 0.00083843997,\n", + " -0.022395005,\n", + " 0.006482994,\n", + " 0.028651446,\n", + " -0.011440122,\n", + " 0.005150829,\n", + " 0.010992955,\n", + " -0.053774204,\n", + " 0.11025878,\n", + " 0.008214591,\n", + " 0.034915168,\n", + " 0.006734031,\n", + " 0.071137644,\n", + " 0.0007473978,\n", + " 0.0030503934,\n", + " 0.008741315,\n", + " 0.023735357,\n", + " 0.013980801,\n", + " 0.013177856,\n", + " 0.029854268,\n", + " 0.046920385,\n", + " -0.02960938,\n", + " -0.04344335,\n", + " -0.008770195,\n", + " 0.005110264,\n", + " -0.015945116,\n", + " -0.035708215,\n", + " 0.013059246,\n", + " 0.01971841,\n", + " 0.011224667,\n", + " 0.027569195,\n", + " 0.06170682,\n", + " 0.019510545,\n", + " 0.0022188863,\n", + " 0.024892962,\n", + " 0.006424488,\n", + " -0.0036090515,\n", + " 0.06568954,\n", + " -0.015655326,\n", + " 0.010469926,\n", + " -0.061592937,\n", + " 0.0043100817,\n", + " -0.033313517,\n", + " 0.036303308,\n", + " -0.003472825,\n", + " -0.02342374,\n", + " -0.025014998,\n", + " 0.022471495,\n", + " -0.07994925,\n", + " -0.01872536,\n", + " -0.021303372,\n", + " 0.024599075,\n", + " 0.027735086,\n", + " 0.14824665,\n", + " -0.0456896,\n", + " 0.014300305,\n", + " 0.03312556,\n", + " 0.03444799,\n", + " -0.06708897,\n", + " 0.004239601,\n", + " -0.032036383,\n", + " 0.023367295,\n", + " -0.025686061,\n", + " 0.0024110237,\n", + " 0.06124078,\n", + " -0.024855759,\n", + " 0.031359654,\n", + " -0.01875005,\n", + " -0.03340488,\n", + " -0.015814602,\n", + " 0.0094120195,\n", + " -0.043995585,\n", + " -0.008542137,\n", + " 0.024300741,\n", + " 0.032288793,\n", + " -0.0013875114,\n", + " -0.019588053,\n", + " 0.027253438,\n", + " -0.05210502,\n", + " -0.037047185,\n", + " 0.018336035,\n", + " -0.0027175995,\n", + " 0.024460023,\n", + " 0.008385286,\n", + " 0.029484948,\n", + " 0.0021098796,\n", + " 0.003140468,\n", + " -0.031146022,\n", + " -0.043809425,\n", + " 0.02471543,\n", + " 0.005733976,\n", + " -0.023251366,\n", + " 0.02595415,\n", + " 0.017859114,\n", + " -0.050796635,\n", + " 0.00884804,\n", + " -0.031136574,\n", + " -0.0036211,\n", + " -0.006290338,\n", + " 0.044331662,\n", + " 0.007915345,\n", + " 0.004572766,\n", + " 0.0010671264,\n", + " -0.00742993,\n", + " 0.027130095,\n", + " 0.03541406,\n", + " 0.011719837,\n", + " -0.010450444,\n", + " -0.032455105,\n", + " -0.016336476,\n", + " 0.04392271,\n", + " 0.0049837725,\n", + " 0.03821958,\n", + " 0.059777457,\n", + " 0.009425316,\n", + " 0.0038634965,\n", + " 0.0069770236,\n", + " -0.0537969,\n", + " -0.048112135,\n", + " 0.00559711,\n", + " 0.027470322,\n", + " -0.044646565,\n", + " -0.07993179,\n", + " -0.004917187,\n", + " 0.021244297,\n", + " 0.014287805,\n", + " 0.036142014,\n", + " 0.0012862032,\n", + " -0.024688799,\n", + " 0.0015671145,\n", + " 0.057700757,\n", + " 0.049819138,\n", + " -0.058502465,\n", + " 0.085045055,\n", + " -0.020705963,\n", + " -0.044569276,\n", + " -0.00055668765,\n", + " -0.009131631,\n", + " 0.020861601,\n", + " 0.042134173,\n", + " 0.0129635045,\n", + " 0.06391071,\n", + " -0.049672384,\n", + " 0.046645127,\n", + " -0.027140489,\n", + " 0.008348439,\n", + " -0.044767596,\n", + " -0.016717143,\n", + " -0.035923313,\n", + " -0.022292176,\n", + " -0.007542445,\n", + " -0.008969496,\n", + " -0.012061755,\n", + " -0.050202377,\n", + " 0.053905237,\n", + " 0.026214758,\n", + " -0.023733322,\n", + " -0.04358869,\n", + " 0.02482057,\n", + " -0.009394614,\n", + " -0.07469014,\n", + " -0.013170866,\n", + " 0.029578324,\n", + " 0.029162087,\n", + " -0.028436398,\n", + " 0.04165277,\n", + " 0.03568401,\n", + " 0.0064282557,\n", + " 0.026195243,\n", + " -0.029818274,\n", + " 0.025353555,\n", + " -0.02269713,\n", + " 0.025988407,\n", + " 0.02207938,\n", + " -0.014281597,\n", + " -0.04456545,\n", + " 0.0014086809,\n", + " -0.037698995,\n", + " 0.023803687,\n", + " -0.0027242722,\n", + " -0.01891849,\n", + " 0.047836542,\n", + " -0.054733414,\n", + " -0.022390537,\n", + " -0.0010643392,\n", + " 0.012789696,\n", + " 0.080227524,\n", + " 0.03610625,\n", + " 0.019415706,\n", + " -0.046773214,\n", + " -0.048641067,\n", + " 0.013460196,\n", + " -0.011560607,\n", + " -0.0033479875,\n", + " 0.042660754,\n", + " -0.05731083,\n", + " -0.028147407,\n", + " 0.008415662,\n", + " 0.012787636,\n", + " 0.0024955238,\n", + " -0.005875471,\n", + " -0.013299467,\n", + " 0.037166175,\n", + " 0.0057459143,\n", + " 0.012639692,\n", + " -0.015172107,\n", + " -0.022445424,\n", + " 0.017624319,\n", + " 0.009638046,\n", + " -0.046090864,\n", + " -0.0060588145,\n", + " -0.043850314,\n", + " 0.03045057,\n", + " -0.038855284,\n", + " 0.045535054,\n", + " 0.009548614,\n", + " 0.011949054,\n", + " -0.007565267,\n", + " 0.029646084,\n", + " -0.023318162,\n", + " -0.0033369183,\n", + " -0.035498414,\n", + " 0.062240385,\n", + " -0.018729104,\n", + " -0.04776792,\n", + " 0.024890197,\n", + " -0.028041568,\n", + " 0.029823277,\n", + " -0.060630605,\n", + " 0.028923012,\n", + " 0.0063285865,\n", + " -0.020326551,\n", + " 0.023190375,\n", + " 0.022982161,\n", + " 0.016292645,\n", + " 0.03233532,\n", + " -0.031412743,\n", + " 0.034803633,\n", + " 0.041211806,\n", + " 0.026718382,\n", + " 0.028487919,\n", + " 0.0359467,\n", + " -0.06362591,\n", + " -0.030659683,\n", + " -0.01509082,\n", + " -0.020952778,\n", + " 0.011969293,\n", + " 0.023588603,\n", + " 0.022859022,\n", + " -0.092516154,\n", + " 0.013380597,\n", + " -0.034692783,\n", + " -0.026464676,\n", + " -0.03864589,\n", + " -0.0037144811,\n", + " -0.028045015,\n", + " -0.018442508,\n", + " 0.036016736,\n", + " 0.008804359,\n", + " -0.003898757,\n", + " -0.009917567,\n", + " -0.03118676,\n", + " -0.026093764,\n", + " -0.04284072,\n", + " -0.03664036,\n", + " -0.018243145,\n", + " -0.017400395,\n", + " -0.011264005,\n", + " -0.07358787,\n", + " -0.057193514,\n", + " 0.050511945,\n", + " -0.028301546,\n", + " -0.016631387,\n", + " 0.05484464,\n", + " 0.007213607,\n", + " -0.034849387,\n", + " 0.068434425,\n", + " 0.012187549,\n", + " 0.0073545114,\n", + " 0.038115777,\n", + " -0.019442376,\n", + " 0.0088192,\n", + " 0.02426156,\n", + " -0.025240779,\n", + " 0.015097276,\n", + " 0.02413101,\n", + " -0.060335062,\n", + " 0.013571056,\n", + " 0.013849029,\n", + " -0.029186107,\n", + " -0.006919429,\n", + " -0.04999688,\n", + " -0.01516865,\n", + " -0.033374574,\n", + " 0.050494786,\n", + " 0.0081956405,\n", + " -0.000781171,\n", + " 0.1156525,\n", + " -0.0032045883,\n", + " -0.04926413,\n", + " 0.021553678,\n", + " 0.011936843,\n", + " 0.044372372,\n", + " 0.06430836,\n", + " -0.057773627,\n", + " 0.039314836,\n", + " -0.02601572,\n", + " -0.0064663533,\n", + " -0.017725777,\n", + " -0.011883558,\n", + " 0.06588944,\n", + " 0.0027787196,\n", + " -0.0057342756,\n", + " -0.0026902868,\n", + " 0.010756356,\n", + " 0.006683054,\n", + " -0.011171504,\n", + " -0.010028028,\n", + " 0.03280309,\n", + " -0.03710007,\n", + " -0.00037581357,\n", + " -0.010274363,\n", + " 0.014990174,\n", + " 0.023026982,\n", + " 0.00462088,\n", + " -0.018528085,\n", + " 0.031811867,\n", + " -0.044433616,\n", + " 0.0017737364,\n", + " 0.020088844,\n", + " -0.0022534393,\n", + " -0.008028976,\n", + " -0.026758444,\n", + " -0.014790072,\n", + " -0.0027231018,\n", + " -0.024185179,\n", + " 0.022362713,\n", + " 0.037899133,\n", + " 0.023111207,\n", + " 0.035417896,\n", + " -0.014735656,\n", + " 0.014920871,\n", + " -0.018102232,\n", + " 0.003849651,\n", + " 0.014768346,\n", + " -0.0047033275,\n", + " 0.0076877363,\n", + " -0.08941378,\n", + " 0.04385689,\n", + " -0.02061675,\n", + " -0.0022157985,\n", + " 0.021340441,\n", + " 0.008795498,\n", + " -0.023795376,\n", + " 0.039326064,\n", + " -0.054837987,\n", + " -0.049411677,\n", + " -0.011908158,\n", + " 0.011915023,\n", + " 0.034715824,\n", + " 0.014839867,\n", + " -0.003681896,\n", + " 0.07058819,\n", + " -0.02855893,\n", + " 0.050516546,\n", + " -0.019206159,\n", + " 0.015897363,\n", + " -0.024837745,\n", + " 0.029461285,\n", + " 0.010113613,\n", + " 0.007867647,\n", + " 0.026553452,\n", + " -0.033507638,\n", + " -0.01779466,\n", + " 0.012894055,\n", + " 0.00731373,\n", + " -0.027972303,\n", + " 0.023625279,\n", + " 0.046873078,\n", + " -0.01835527,\n", + " 0.025398996,\n", + " -0.00947968,\n", + " 0.011787183,\n", + " 0.048391055,\n", + " 0.011638939,\n", + " 0.003961612,\n", + " 0.020612521,\n", + " 0.00543749,\n", + " 0.031116953,\n", + " 0.038547985,\n", + " -0.028023694,\n", + " 0.029720454,\n", + " -0.044062383,\n", + " -0.04660935,\n", + " 0.017674532,\n", + " -0.024052268,\n", + " 0.031557217,\n", + " 0.008316933,\n", + " 0.012430458,\n", + " -0.038235627,\n", + " -0.007937035,\n", + " -0.00097407197,\n", + " 0.031212503],\n", + " 'lg_s': 'fr',\n", + " '_version_': 1843523311038889984,\n", + " '_root_': 'GDL-1912-01-25-a-i0001-s-29'},\n", + " {'id': 'GDL-1912-01-25-a-i0001-s-70',\n", + " 'type_s': 's',\n", + " 'content_txt_fr': \"port est accordée aux éditeurs de journaux quotidiens et de publications périodiques sud-américains pour les exemplaires jusqu' au nombre de deux échangés par.\",\n", + " 'ci_id_s': 'GDL-1912-01-25-a-i0001',\n", + " 'gte_multi_v768': [-0.05680408,\n", + " 0.06387808,\n", + " -0.04856367,\n", + " 0.07558254,\n", + " -0.021889713,\n", + " 0.027441371,\n", + " 0.0015161067,\n", + " 0.027526896,\n", + " 0.070930585,\n", + " -0.058298152,\n", + " -0.011244095,\n", + " 0.047598463,\n", + " -0.030812727,\n", + " 0.04946567,\n", + " -0.1109161,\n", + " 0.075338885,\n", + " 0.09431828,\n", + " 0.065175645,\n", + " 0.048616614,\n", + " -0.015955964,\n", + " 0.060905457,\n", + " 0.004543543,\n", + " -0.015062949,\n", + " 0.027204664,\n", + " -0.012537254,\n", + " 0.109382056,\n", + " -0.0058181244,\n", + " -0.03267176,\n", + " -0.038578954,\n", + " 0.01801676,\n", + " -0.08267891,\n", + " -0.034785353,\n", + " 0.04281231,\n", + " 0.025842642,\n", + " 0.03903481,\n", + " 0.022392912,\n", + " -0.008075021,\n", + " -0.003958624,\n", + " 0.028308881,\n", + " 0.034027323,\n", + " -0.017764986,\n", + " -0.027231509,\n", + " -0.029520093,\n", + " 0.010817953,\n", + " 0.017693274,\n", + " 0.06503678,\n", + " -0.071917005,\n", + " 0.02230548,\n", + " 0.005966704,\n", + " 0.021682076,\n", + " -0.034017008,\n", + " 0.03497421,\n", + " 0.016124977,\n", + " 0.07258827,\n", + " 0.06323594,\n", + " 0.042673863,\n", + " -0.07751493,\n", + " 0.032996166,\n", + " 0.08310853,\n", + " -0.018388394,\n", + " 0.0512766,\n", + " -0.0032999113,\n", + " -0.025261564,\n", + " -0.008211472,\n", + " -0.006080969,\n", + " -0.030746382,\n", + " 0.018559372,\n", + " -0.026786452,\n", + " 0.10291751,\n", + " 0.044018302,\n", + " -0.044262085,\n", + " 0.03787636,\n", + " -0.023074595,\n", + " 0.03189656,\n", + " -0.022342745,\n", + " 0.02490987,\n", + " 0.0610374,\n", + " 0.05679413,\n", + " -0.015448033,\n", + " 0.04165428,\n", + " -0.041415293,\n", + " -0.04143148,\n", + " 0.033411153,\n", + " 0.027957879,\n", + " -0.05191326,\n", + " -0.021843795,\n", + " -0.0069933883,\n", + " 0.03257855,\n", + " -0.040802136,\n", + " -0.0039164457,\n", + " 0.051885936,\n", + " 0.08618492,\n", + " -0.00050581986,\n", + " -0.028928392,\n", + " 0.029504543,\n", + " 0.07240461,\n", + " -0.034900557,\n", + " 0.019995965,\n", + " 0.11230153,\n", + " 0.011365759,\n", + " -0.0054779435,\n", + " 0.018395215,\n", + " 0.02106766,\n", + " -0.03626866,\n", + " 0.028840657,\n", + " 0.019836048,\n", + " 0.022810984,\n", + " -0.0008726806,\n", + " 0.015734892,\n", + " -0.025800215,\n", + " -0.04126276,\n", + " -0.01494636,\n", + " -0.08921718,\n", + " -0.026337288,\n", + " 0.028740907,\n", + " -0.020959945,\n", + " 0.049158905,\n", + " -0.07213806,\n", + " 0.0026235483,\n", + " 0.047008693,\n", + " -0.03597703,\n", + " 0.012278491,\n", + " -0.078883186,\n", + " -0.022993986,\n", + " -0.07842844,\n", + " 0.006434972,\n", + " -0.047524337,\n", + " -0.06447543,\n", + " -0.0060534813,\n", + " -0.00589939,\n", + " 0.0760615,\n", + " 0.015441079,\n", + " 0.01964648,\n", + " 0.0011932348,\n", + " 0.06662931,\n", + " -0.023894684,\n", + " 0.017201254,\n", + " 0.07950517,\n", + " 0.035065234,\n", + " -0.032788448,\n", + " -0.05365816,\n", + " -0.005709627,\n", + " -0.052723065,\n", + " 0.05486205,\n", + " 0.023403581,\n", + " -0.014603613,\n", + " -0.021162527,\n", + " -0.052467994,\n", + " -0.03011303,\n", + " 0.0011532663,\n", + " 0.0003995073,\n", + " 0.0360547,\n", + " -0.011495599,\n", + " -0.04326665,\n", + " 0.024591248,\n", + " -0.03959948,\n", + " 0.03528982,\n", + " 0.06305916,\n", + " 0.017708087,\n", + " -0.017182063,\n", + " 0.0017088845,\n", + " 0.04461511,\n", + " -0.0039479155,\n", + " -0.043220203,\n", + " -0.047296237,\n", + " -0.010154965,\n", + " -0.028041942,\n", + " 0.0446806,\n", + " 0.03756078,\n", + " 0.020877628,\n", + " -0.07659133,\n", + " 0.03962669,\n", + " 0.029327717,\n", + " -0.015903363,\n", + " -0.035756286,\n", + " 0.04176602,\n", + " -0.02734469,\n", + " -0.0030521317,\n", + " -0.014741279,\n", + " 0.07573669,\n", + " 0.05783421,\n", + " -0.01144547,\n", + " -0.043425426,\n", + " -0.0663662,\n", + " 0.024635118,\n", + " -0.014225987,\n", + " 0.03249727,\n", + " 0.014217647,\n", + " 0.004667845,\n", + " 0.0358217,\n", + " -0.0242047,\n", + " -0.06522303,\n", + " -0.058395717,\n", + " 0.016197577,\n", + " -0.037792005,\n", + " -0.027401919,\n", + " -0.02850256,\n", + " 0.031710375,\n", + " -0.01611329,\n", + " 0.0021421046,\n", + " 0.012047816,\n", + " 0.020715512,\n", + " 0.039120678,\n", + " 0.021670764,\n", + " 0.0047489484,\n", + " -0.032356948,\n", + " 0.009116835,\n", + " -0.03439566,\n", + " -0.023327397,\n", + " -0.016594242,\n", + " 0.0014536829,\n", + " 0.009252665,\n", + " 0.0051945024,\n", + " -0.0043386198,\n", + " -0.040954057,\n", + " -0.020179464,\n", + " -0.05918961,\n", + " -0.0303645,\n", + " 0.037603993,\n", + " -0.008280048,\n", + " -0.0051193824,\n", + " -0.016355518,\n", + " -0.03947001,\n", + " -0.037388187,\n", + " -0.0053553856,\n", + " 0.020274382,\n", + " -0.019270543,\n", + " 0.022108195,\n", + " 0.0063307756,\n", + " -0.039626062,\n", + " 0.022539085,\n", + " -0.016099013,\n", + " 0.025176348,\n", + " 0.019320844,\n", + " -0.011700732,\n", + " 0.009495598,\n", + " 0.036385875,\n", + " 0.066322245,\n", + " -0.021529708,\n", + " 0.056870252,\n", + " 0.034732975,\n", + " -0.030924838,\n", + " 0.038632993,\n", + " 0.029679107,\n", + " -0.013694661,\n", + " 0.027893692,\n", + " -0.038053572,\n", + " -0.016527917,\n", + " -0.03648918,\n", + " 0.009421407,\n", + " -0.027731346,\n", + " 0.011813313,\n", + " 0.0126533,\n", + " 0.006421953,\n", + " -0.046381734,\n", + " -0.012230512,\n", + " 0.015225633,\n", + " -0.01651272,\n", + " 0.03236237,\n", + " -0.051103573,\n", + " -0.052263077,\n", + " 0.015807312,\n", + " -0.013421665,\n", + " -0.05319022,\n", + " 0.03754047,\n", + " -0.08575125,\n", + " 0.019848185,\n", + " 0.07780862,\n", + " -0.025172248,\n", + " -0.017809829,\n", + " 0.0054981536,\n", + " 0.02206488,\n", + " -0.0402048,\n", + " 0.05657433,\n", + " -0.052837722,\n", + " -0.03221729,\n", + " -0.017220937,\n", + " -0.020376498,\n", + " -0.01109481,\n", + " 0.015917942,\n", + " 0.025976157,\n", + " -0.023923505,\n", + " 0.01464813,\n", + " -0.018986428,\n", + " -0.011994399,\n", + " 0.0077301194,\n", + " 0.023208115,\n", + " -0.027664742,\n", + " -0.025231324,\n", + " 0.034364924,\n", + " -0.035596997,\n", + " -0.010281778,\n", + " -0.01776035,\n", + " -0.007292064,\n", + " 0.000418178,\n", + " -0.006930773,\n", + " -0.056325603,\n", + " 0.021520996,\n", + " 0.041496553,\n", + " 0.0063503096,\n", + " -0.036979865,\n", + " -0.03306839,\n", + " 0.03575481,\n", + " 0.039904743,\n", + " 0.036307413,\n", + " -0.044993307,\n", + " -0.022727903,\n", + " -0.017485218,\n", + " -0.085646205,\n", + " 0.017956333,\n", + " -0.0024675934,\n", + " 0.01523081,\n", + " -0.03383787,\n", + " -0.018295113,\n", + " 0.040419225,\n", + " 0.03375754,\n", + " -0.0061179134,\n", + " 0.02837869,\n", + " -0.06238745,\n", + " -0.0021848788,\n", + " -0.055100147,\n", + " 0.04505286,\n", + " 0.009902881,\n", + " -0.0011387669,\n", + " -0.0072524976,\n", + " -0.02486218,\n", + " 0.05738864,\n", + " 0.023359027,\n", + " -0.024014225,\n", + " -0.02835716,\n", + " 0.0062544495,\n", + " 0.017787637,\n", + " 0.01560684,\n", + " -0.05617647,\n", + " 0.012903993,\n", + " 0.044633143,\n", + " 0.026930042,\n", + " 0.010915518,\n", + " 0.05127232,\n", + " 0.029528333,\n", + " 0.024195252,\n", + " 0.053241197,\n", + " -0.0640872,\n", + " -0.03625579,\n", + " 0.007576901,\n", + " 0.010667519,\n", + " 0.09268224,\n", + " 0.011553675,\n", + " 0.01267877,\n", + " -0.02053662,\n", + " -0.009395332,\n", + " 0.008464381,\n", + " 0.020977568,\n", + " -0.01891739,\n", + " 0.032037094,\n", + " -0.020472875,\n", + " -0.010507396,\n", + " 0.07543627,\n", + " -0.038927633,\n", + " 0.064642675,\n", + " 0.043160703,\n", + " -0.0014504181,\n", + " -0.022373311,\n", + " 0.027925998,\n", + " 0.014306418,\n", + " -0.014883518,\n", + " -0.011328613,\n", + " 0.05313789,\n", + " 0.020786073,\n", + " -5.2853888e-05,\n", + " -0.002864547,\n", + " 0.020562628,\n", + " -0.019998584,\n", + " 0.10793451,\n", + " -0.04854008,\n", + " -0.03561407,\n", + " 0.00051874836,\n", + " -0.01930007,\n", + " 0.008874648,\n", + " 0.018628655,\n", + " 0.0150350705,\n", + " -0.023917707,\n", + " 0.031191936,\n", + " -0.018240798,\n", + " 0.02280116,\n", + " 0.031054737,\n", + " -0.043735705,\n", + " -0.049130388,\n", + " -0.020346304,\n", + " -0.044371933,\n", + " 0.0049108826,\n", + " -0.032801054,\n", + " 0.014804224,\n", + " 0.019464063,\n", + " -0.025238449,\n", + " -0.01920073,\n", + " 0.06630683,\n", + " 0.0370241,\n", + " 0.021422138,\n", + " 0.0237387,\n", + " 0.026918953,\n", + " 0.014984069,\n", + " 0.05003196,\n", + " -0.013169837,\n", + " 0.025115224,\n", + " -0.022145707,\n", + " 0.039328806,\n", + " -0.056289665,\n", + " 0.002686336,\n", + " -0.010678451,\n", + " 0.022610897,\n", + " -0.025488157,\n", + " 0.043593667,\n", + " -0.09402724,\n", + " 0.07852914,\n", + " -0.008758481,\n", + " 0.016202908,\n", + " 0.058471553,\n", + " 0.15999767,\n", + " -0.0017225927,\n", + " 0.0067002787,\n", + " 0.053081356,\n", + " 0.016023297,\n", + " -0.070710465,\n", + " -0.0056044315,\n", + " 0.036097743,\n", + " 0.037961904,\n", + " 0.0081612505,\n", + " -0.011321509,\n", + " 0.004900642,\n", + " -0.008063335,\n", + " 0.021463236,\n", + " -0.05130153,\n", + " -0.0652861,\n", + " -0.023450883,\n", + " 0.04997369,\n", + " 0.00024382243,\n", + " -0.04580109,\n", + " 0.021559305,\n", + " 0.024988277,\n", + " -0.013621296,\n", + " -0.0347862,\n", + " 0.030518003,\n", + " -0.018858507,\n", + " -0.050935045,\n", + " -0.0044698385,\n", + " 0.0074550062,\n", + " 0.049126945,\n", + " -0.038395636,\n", + " 0.047106765,\n", + " -0.027374133,\n", + " 0.016838936,\n", + " -0.030900508,\n", + " -0.0507253,\n", + " -0.00081984577,\n", + " 0.010674338,\n", + " -0.020206412,\n", + " 0.0151003385,\n", + " -0.042421304,\n", + " -0.027443845,\n", + " 0.0043962398,\n", + " -0.023046808,\n", + " -0.0029031036,\n", + " -0.044903956,\n", + " -0.022942783,\n", + " -0.0033205838,\n", + " 0.023103176,\n", + " 0.017453719,\n", + " -0.05724227,\n", + " 0.02223993,\n", + " 0.0045749834,\n", + " -0.0057145464,\n", + " 0.0055112913,\n", + " -0.022596361,\n", + " -0.049288895,\n", + " 0.052903038,\n", + " -0.032930087,\n", + " 0.044564545,\n", + " 0.037451547,\n", + " -0.008487822,\n", + " -0.00046948888,\n", + " 0.014867911,\n", + " -0.034751162,\n", + " -0.0073387115,\n", + " 0.026934503,\n", + " 0.014844265,\n", + " 0.008190351,\n", + " -0.045524325,\n", + " -0.0033880551,\n", + " 0.024464807,\n", + " 0.049926214,\n", + " 0.048998564,\n", + " 0.020574521,\n", + " 0.026498424,\n", + " 0.025967795,\n", + " 0.080135554,\n", + " -0.02498737,\n", + " -0.023838338,\n", + " 0.0589479,\n", + " -0.006773478,\n", + " -0.039905064,\n", + " -0.0062658098,\n", + " 0.045033496,\n", + " 0.06459868,\n", + " 0.002900991,\n", + " 0.0038800703,\n", + " 0.06322735,\n", + " 0.00029259123,\n", + " 0.025133284,\n", + " -0.048754428,\n", + " 0.00070420036,\n", + " -0.021258762,\n", + " -0.04107931,\n", + " -0.015941324,\n", + " -0.071368955,\n", + " -0.024546072,\n", + " -0.006689376,\n", + " 0.029536944,\n", + " -0.046778042,\n", + " 0.04152148,\n", + " 0.018942926,\n", + " -0.0067904987,\n", + " -0.044583526,\n", + " 0.017837103,\n", + " 0.04061375,\n", + " -0.052083123,\n", + " 0.0236291,\n", + " 0.01284286,\n", + " 0.0171025,\n", + " -0.02275749,\n", + " 0.033556618,\n", + " 0.004836787,\n", + " 0.03009814,\n", + " -0.052731037,\n", + " 0.013754754,\n", + " 0.053202175,\n", + " 0.010482435,\n", + " 0.04622099,\n", + " 0.019243684,\n", + " 5.367547e-05,\n", + " -0.011120939,\n", + " -0.02151325,\n", + " -0.04548332,\n", + " -0.022005042,\n", + " -0.018184977,\n", + " -0.036811054,\n", + " 0.019177958,\n", + " -0.06955333,\n", + " -0.0231974,\n", + " -0.028599884,\n", + " -0.027384752,\n", + " 0.033006314,\n", + " 0.011088715,\n", + " 0.0069307997,\n", + " -0.028356984,\n", + " -0.01316145,\n", + " 0.062719725,\n", + " 0.008206823,\n", + " -0.019569961,\n", + " -0.014994998,\n", + " -0.031228635,\n", + " -0.029914973,\n", + " 0.060132407,\n", + " 0.014801324,\n", + " 0.033433307,\n", + " 0.014585036,\n", + " -0.03210837,\n", + " -0.009049988,\n", + " -0.03037654,\n", + " 0.029199922,\n", + " -0.055459544,\n", + " -0.017411731,\n", + " 0.009728488,\n", + " -0.030245861,\n", + " -0.01829823,\n", + " -0.0068603996,\n", + " -0.017303465,\n", + " 0.010572903,\n", + " -0.02823631,\n", + " 0.051125452,\n", + " -0.032821577,\n", + " -0.007214039,\n", + " -0.024644949,\n", + " 0.027078621,\n", + " -0.03712036,\n", + " 0.0048836297,\n", + " -0.084682174,\n", + " 0.012341536,\n", + " -0.025374034,\n", + " -0.046953052,\n", + " 0.015795348,\n", + " -0.010103081,\n", + " 0.009278835,\n", + " -0.03617463,\n", + " 0.031759385,\n", + " 0.003919212,\n", + " 0.017071849,\n", + " -0.02655857,\n", + " 0.0028727693,\n", + " -0.008133552,\n", + " 0.0041895863,\n", + " -0.031180326,\n", + " 0.09085531,\n", + " 0.026876906,\n", + " 0.009257815,\n", + " 0.06918902,\n", + " 0.010982239,\n", + " -0.063372925,\n", + " -0.037140924,\n", + " 0.009987525,\n", + " -0.013391082,\n", + " 0.006153766,\n", + " 0.02854545,\n", + " 0.029123561,\n", + " -0.03588052,\n", + " 0.011743845,\n", + " -0.055579346,\n", + " -0.011289578,\n", + " -0.0044937357,\n", + " 0.0076637147,\n", + " -0.023567881,\n", + " 2.3369465e-05,\n", + " 0.025043108,\n", + " 0.021869775,\n", + " 0.054185614,\n", + " 0.006243622,\n", + " -0.054999202,\n", + " -0.055334296,\n", + " -0.0647816,\n", + " -0.01704009,\n", + " -0.053713467,\n", + " -0.04823133,\n", + " -0.014942541,\n", + " -0.05840356,\n", + " -0.012674364,\n", + " -0.003911387,\n", + " -0.050819866,\n", + " 0.00014474818,\n", + " 0.073844366,\n", + " 0.010522974,\n", + " 0.0015996089,\n", + " 0.008558171,\n", + " 0.010174858,\n", + " -0.028922917,\n", + " 0.029761026,\n", + " 0.010588534,\n", + " 0.017381694,\n", + " 0.009115375,\n", + " -0.018989211,\n", + " -0.003194415,\n", + " 0.013919865,\n", + " -0.03536051,\n", + " -0.032564633,\n", + " -0.026487092,\n", + " 0.020456523,\n", + " -0.0011054155,\n", + " -0.024419568,\n", + " -0.005077697,\n", + " -0.0095237745,\n", + " 0.084264286,\n", + " 0.022982834,\n", + " -0.014327535,\n", + " 0.15581359,\n", + " -0.023523292,\n", + " -0.0504727,\n", + " 0.031755354,\n", + " 0.015520586,\n", + " 0.05364135,\n", + " 0.058876373,\n", + " -0.02043425,\n", + " 0.048008807,\n", + " -0.0073660137,\n", + " -0.0052846954,\n", + " -0.024466448,\n", + " -0.014896462,\n", + " 0.010465434,\n", + " 0.0029648398,\n", + " -0.08468755,\n", + " -0.030296,\n", + " -0.0006499835,\n", + " -0.017287035,\n", + " -0.008246593,\n", + " -0.032095876,\n", + " 0.009795486,\n", + " -0.025566109,\n", + " 0.024589794,\n", + " -0.011263848,\n", + " 0.012535761,\n", + " 0.0023695156,\n", + " 0.007081577,\n", + " 0.014829279,\n", + " 0.017556475,\n", + " 0.0044162525,\n", + " 0.018217932,\n", + " 0.01936434,\n", + " -0.014689975,\n", + " -0.014862805,\n", + " -0.0339685,\n", + " 0.018071441,\n", + " -0.014117345,\n", + " 0.010728882,\n", + " 0.0010798945,\n", + " 0.0013677074,\n", + " -0.0035509395,\n", + " 0.0023138344,\n", + " -0.02207691,\n", + " 0.027792078,\n", + " -0.022042053,\n", + " 0.007442902,\n", + " -0.0030612324,\n", + " -0.009760814,\n", + " 0.037549023,\n", + " -0.02928992,\n", + " 0.05390074,\n", + " -0.019230692,\n", + " -0.012139241,\n", + " 0.001288939,\n", + " -0.011020472,\n", + " -0.043356016,\n", + " 0.05652876,\n", + " -0.042325146,\n", + " -0.013620406,\n", + " 0.0029760897,\n", + " 0.008271474,\n", + " 0.007846904,\n", + " 0.0011568316,\n", + " -0.013965066,\n", + " 0.047694013,\n", + " 0.013437404,\n", + " 0.034186125,\n", + " 0.013992624,\n", + " 0.042957436,\n", + " -0.017203378,\n", + " 0.061278712,\n", + " -0.005151349,\n", + " -0.02090346,\n", + " 0.014107725,\n", + " -4.5311303e-05,\n", + " -0.0111748595,\n", + " 0.01584758,\n", + " 0.01897466,\n", + " -0.03805934,\n", + " -0.022197109,\n", + " 0.03860355,\n", + " 0.0014635735,\n", + " 0.047886554,\n", + " 0.020262355,\n", + " 0.014944389,\n", + " 0.0116559435,\n", + " -0.01366922,\n", + " -0.046399254,\n", + " 0.011021824,\n", + " 0.00818818,\n", + " -0.013689622,\n", + " 0.030283738,\n", + " -0.0039186855,\n", + " 0.0021658074,\n", + " 0.056276754,\n", + " -0.023511963,\n", + " 0.0066836593,\n", + " -0.048657592,\n", + " 0.001489622,\n", + " 0.00783965,\n", + " -0.0446165,\n", + " -0.025651837,\n", + " 0.018622568,\n", + " 0.022268912,\n", + " 0.04480489],\n", + " 'lg_s': 'fr',\n", + " '_version_': 1843523311160524800,\n", + " '_root_': 'GDL-1912-01-25-a-i0001-s-70'}]" + ] + }, + "execution_count": 76, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "docs" + ] + }, + { + "cell_type": "code", + "execution_count": 77, "id": "fcc6262c", "metadata": {}, "outputs": [ @@ -206,42 +3471,60 @@ "name": "stdout", "output_type": "stream", "text": [ - "A catte occa.\n", - "C' est.\n", - "C' est.\n" + "--- Result 0 ---\n", + "En outre, la nouvelle convention accorde la franchise de port pour la correspondance drdniaire des institutions nationales ayant un caractère scientifique et d' intérêt général ; ainsi qu' aux congrès scientifiques sud-américains composés de la majorité des pays de ce continent.\n", + "[No text]\n", + "--- Result 1 ---\n", + "Certaines dispositions insérées dans la nouvelle convention sud-américaine ont sans contredit une portée autre que simplement postale.\n", + "[No text]\n", + "--- Result 2 ---\n", + "port est accordée aux éditeurs de journaux quotidiens et de publications périodiques sud-américains pour les exemplaires jusqu' au nombre de deux échangés par.\n", + "[No text]\n" ] } ], "source": [ - "for doc in result['solrResponse']['response']['docs']:\n", - " print(doc['content_txt_fr'][:200]) # first 200 characters of the document content" + "for i, d in enumerate(docs):\n", + " print(f\"--- Result {i} ---\")\n", + " print(d.get(\"content_txt_fr\", \"[No text]\"))\n", + " print(d.get(\"content_txt_de\", \"[No text]\"))" + ] + }, + { + "cell_type": "markdown", + "id": "9822c685-ca20-4277-b4a5-a26290350627", + "metadata": {}, + "source": [ + "#### Sentence Embeddings - Out-of-corpus queries\n" ] }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 78, "id": "5e6798ed", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "'gte-768:ddeJvRe+8TxHOBA9/0EnvbjyubyCSpa9f7kZvfnyzD0/kDo9SV9FvZmMwbyarJc9MMDRvXBQgDySVLy8f9GYPfvy2j1OKVM99wcVPfDZgbyaaJ49WpYmPKOnGLweJCM9zmfHPHZpZT11z0A9FBQ3vWGspL3f3W07ahTyvAufhrxrMVG9zbtivXr+yD26Weq6zegRPYyOv7w6eJ08TdeuPK+2E71tFQ29wS4CvRU/Czt4gYS8Ps4Eu3Y/Xb0l08U9IIdcPGMxFTzxZQQ8n+npvBTgajrIcGI9wZjDPJ2fKzxz9Nu9LI6AvLI+DD25S/m8JJCAPbu5Fbu5gSW9PytTvLBFDb0T/0A80lPOPP6WkryVmOE9O8UuPf2tWL0DxJi8LrcPvS8zpztEn3+8qXSFPYjqpLyn1Ng7NN0bvfS6g7tew+K8jSX8vI0vgjwLGq08rj/fvCgZmL2XPPK8cE0GPcQ5ibzKEFY9YoafPZUQsDvSMz09hokjvM+/azsl/Sq8pwKku/QkkjwIhKS7LXIJvC3dYbwoGX49QX+tPejoxzxgMPY89EwXvSyfQDpojAg5+6O4vQyjOT3klXq8Wy6/vW0XYjv1LGK9L+n8vPTCnbwn9km9UyD7OuVwbjzQqCK9bPRAvFlugDxES1e9guGIvOqur72rQv08oTo9vduE6jwZy908Agf0vAWnjD0uSQq9nx14PJyUuLzkZnE9tq2svGgbLz2EgXQ9kjpjPEs6Bb2VHtu9X9JqO3iElr0UBYU7efgkvCrWUD2GjGW94ilKvLX/FzxIYCc99cRYu01vPjyAmaA8+WszvUa2hjwWNsk8IPSLO2P04TtBupC8l+eIvG0V4z29JF49fFQFvJCgwryb9xq9JccovWssD70AVGa8jp9yPZaQgzz/Vye9FiQoPbC7szyaDI+6xxrRvDp2HT0R4sE8BxLIPBE6Xb3VUvQ84eBxPAPBk72TZ0C8hdQ5u2n20zqKip+8UPmAveJRWj07PGq835D9PDGkBL37BjI9f8GcvVv2qzyY1cC6Pk4lvcg9Kr2Ts3g8TeVrvXmuWT3HSx09XL5yvF+TCj15kaw8nOcRvLYHCL3n+n283diAvZr8B7vYzjW9FvtIPADcwTx9Kog8x0WUPGYUNzwP8x+9R8kKvQr/Ab2QIlM8MwhOvfurKjsdogC91RgMPMUA0bvKI1E96LhGPHwX1rtvYzA9Wv2lPNyBD700FNY56icNPZc66Txk+CO6oDxMvFowg7zwFJw8d34yPXS9bLzJEZc9VdVYPY89G7xPAwW8b4FsPJnmuLwL3dI7S84jPNllLTrR2tm7ynSQOwz317wi79Q8xlVyvd2KwTzMxj08pn0qvfeHHz2O47c86w0FPBgoozwYqTw8m/MCvXkRFrue4kQ9hOqtPBCQv72BQoU9vbCTvGvIRb1U2YC9Xo0uvRQZTDxsnZG8gBMAPR5EkL2ktEc8Zx3eu1z457ujy6S8naeOuxv/E7zxjyA7XvURPJ6hnzvxy8U3pHxfPfgdmzzMWPc8Dns9vflngzywA6u8OdUQvZP/zrxk6N082jqePA8B27x//7i9XooPvIL2Zzwsgay9WeMCOg1mn7v9yri7VE/OO+dARb0d4Yu8fXDEvfslpr12jtu55AfXPKsx17znb8O7xL8fvYfHRzwdwUE9sV/NvDLkc71zAqE8XO2HPI0sEbyXRK88RnQUPj+eaLw1HMI7ER8+vZ8ooryAzds8JLAHPY94wrzMe7S7W1HAvO3k/DufShQ9pb61vM8+LDoBZpu6lwY3Pf5Xurt4ELc8VprFPOr6jbx7LPk8TQJ5vQJTGTyT7/K8cXwMvc1SrDyf2rW81n2hutWZ97tUmyU9h6DSPH6IgzxJEa89BqMWu/OtOz0hjke9sFCxPHili7u/j0u7WyFbPfGEjLtOG5U80U74OkQoYj1Z2DQ9RSdVve0hXT2jPpu82MdhPawxzLwMaAg7Ixi1vERjoT1QNj+95QctPfj8tjzvtia7VUgXPVDdDD022ls8Df2yOtAGDz3LdTa9wJ1NPEC3kbwC3jM9Pjv8Oy0m7bw/w8m7mqAWPS7DlLz6a9E8LH6BPHcUODyTNFe84+eTPeMhGb2JPqY8agfZO5gbKz3qDN88ibWiPJV5Oz3Xv505wfShPYSvOD3atNs732gZvCRgkTki3u884TiOOozJ9DyG9DC9yjnBPAExWTwFewU921eQPDdqIz5O8oS9Ms1/PCvUyzsimqW5G10hvaXC7rwQoU48bmpiPKtBFj2YZqM8fDbjuhxq7zyCh7Q8Y9U2veA/VLwRZ++7rekiPQ3QrrsirOQ8g0ArPHIipbw2pi69w2PTOkeEhTxk6F29JiK7u3UNX7sSJia8lGU0PVJsHzuc2hY8uN6evS3diDu7YNi8tgJMPdiJNz0X/XQ5tq9zvJdrybtwx+Q7tEc8PcSwVr0LlAK9uvfQPFtWZrxSAoA9CKZJugeATjxrRNm6oJPPO8PLszyRx+w7Ygv7PAHukjs6n128CLs5vWT/7Lu7ogm8Sg5qPcWGlTu62mG8hKEhPY0t0bvnl+C7LQiXPLValDyE5Co8z8wnvG2HGL12TLi8acIBPIcxIzyXJCG8ZE46O7mD37xFtkM8nOwuvFxtvrutXQK9/PpFvBk7nDwO9qe8p1hivXMYrjzQv/k8bTapPAipB72xQL88KzcRPNiTO7z+qpQ7LKsPvby6yrxAxms8w6U0O9Con72FGWo81e7IvB701D1g0AM8x6LrvD9MUjwKwVu7U62ZPb4AdjwvdnQ9ukC0u8sWZD1Lwxs9ubgcvGSEbL3YJT+86l/fPLm7BjwEWj89IUvwPPIGKT31ags9elWDvIA/PzwZd8M8N989vWxdtrxuSLm8MLVbvY7GFjzdzoQ7qbBFPKzrpL119uO8bZwevfmKljihXwy9yNdKPDODeD0bm9y8AwgzPNGg5rwVoJe82o1PO6l+lTyKKfA5RWYAPCCzIT3YkOo7XqZSvH3BC7w+mMq8WC9aPUzpp7t3kkI8S4dgvGjehbzNc5A9/SKZPKSpw7tK8yo8e0Xiu3ANGL2/XCa9MzpCu1CI0r0F6Xe9/dL9u4dYX73hDzu9UCTWuWmddLwAU3c9luCsPKjyHbzD+Ne8Qeazu6YIq7wjxcy7Rp6MPFglMrwgy008LCFDvcVGyzwVizQ9bX8dO3sEq7wgmG49hPaqvDaCpD1zWnS8foMnvL6GyrzlW5O8Si3VPBLKcD0vP8+8inFBPFdPgTwKSYo9N0dvPEVKbTs5NsI8trVrPHGjC72vApG8XPFvu5b68jx4kbI8vPCcOyPMlzyxwHw9cHP8PGTaZ73FMpy8uTvqPH+efjtVwTs8rayLPKZzBTpBYh88IMDlvAG2pLyeiD49VD78uwRxQb3Un0U8MJTRPCAca705Q/2756V5PSRVuzt4Mac8lHOdvLDMmzwYmBE8wNIOvHim/7zPNJ08u8m5u7eg0LyF4uy6jHDdvED6KD17J4M9uQCePCpZBzyKF4G87vMFPSnbO71jpxg9rScuPCdhpz1e1OO8cRoRO78VQbwQlPG8TnyAPNoTjTqRyDO96CO1Os9zwbs41lS8vJvmu9Luezw56+K6qZw8PD6VzTxsaZ88QyuHvWDbqb0G5Fs8XHELvO/SHzqRgfM89boPPQc6sTwJHji8mK0NvchYqDw1gvO7xx1IPB/CXbv2BWU7yi6ePFFWlLopvEA8DebUOz5dz7uE2NS84FEqvPkAozwHOpe8cyG8O45gZDuYURe82yE8PbRQCDwyhO28OQ+zvN3ejDxe2sK84l7Mu+gigr17kLg9cA6XvOFJXzxCvKS8xbJjPL9gEb2R0Bg8BBgavNbnmbwZjl+6/KIaO7PsRT1C/CK9AHyHPLCPIj0XAqU7LBPHvNOWvjstmSO9cqSkvCcQJr3Agha5/Hg7vAo+JDwwapY9jHLvvF2qnbsqhJQ8HaSxPYvK7rxZj6g9Fs9GvEFFIjzs84u6acjTOyoof7wnisS7VKW3vI7rCr02g2g9y/MnPA5T0zv+bZ85HDTVPKfQaz0v17y8385EPWtYXD0USP68'" + "'gte-768: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'" ] }, - "execution_count": 44, + "execution_count": 78, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "embedding = impresso.tools.embed_text(text=\"Je suis une théière!\", target=\"text\")\n", + "sentence = \"Le congrès international s'est tenu à Paris pour discuter des avancées scientifiques de la décennie.\"\n", + "\n", + "embedding = impresso.tools.embed_text(text=sentence, target=\"text\")\n", "embedding" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 79, "id": "0e58b62c", "metadata": {}, "outputs": [ @@ -251,7 +3534,7 @@ "768" ] }, - "execution_count": 45, + "execution_count": 79, "metadata": {}, "output_type": "execute_result" } @@ -264,12 +3547,38 @@ "_, arr = embedding.split(':')\n", "arr = base64.b64decode(arr)\n", "outof_corpus_emb = [struct.unpack('f', arr[i:i+4])[0] for i in range(0, len(arr), 4)]\n", + "\n", "len(outof_corpus_emb)" ] }, { "cell_type": "code", - "execution_count": 46, + "execution_count": 80, + "id": "09489886-3fd4-498e-b534-298dda3ce96c", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[0.012716123834252357,\n", + " 0.0367739275097847,\n", + " -0.037758711725473404,\n", + " 0.002986321458593011,\n", + " -0.08889304101467133]" + ] + }, + "execution_count": 80, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "outof_corpus_emb[:5]" + ] + }, + { + "cell_type": "code", + "execution_count": 81, "id": "27b47638", "metadata": {}, "outputs": [ @@ -277,7 +3586,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "Got 3 solr documents\n" + "✅ Got 3 Solr document(s)\n", + "\n" ] } ], @@ -294,12 +3604,13 @@ " }\n", " }\n", ")\n", - "print(f\"Got {len(result['solrResponse']['response']['docs'])} solr documents\")" + "docs = result[\"solrResponse\"][\"response\"][\"docs\"]\n", + "print(f\"✅ Got {len(docs)} Solr document(s)\\n\")" ] }, { "cell_type": "code", - "execution_count": 47, + "execution_count": 82, "id": "4194268d", "metadata": {}, "outputs": [ @@ -307,15 +3618,193 @@ "name": "stdout", "output_type": "stream", "text": [ - "\n", - "Taïaut !\n", - "toi !\n" + "--- Result 0 ---\n", + "[No text]\n", + "Bei der internationalen Delegierten konferenz der Notare han.\n", + "--- Result 1 ---\n", + "[No text]\n", + "l \" \" \" erwähnten Kongreß « « « gesetzte internatio. \" \"\n", + "--- Result 2 ---\n", + "Paris, 10 janvier.\n", + "[No text]\n" + ] + } + ], + "source": [ + "for i, d in enumerate(docs):\n", + " print(f\"--- Result {i} ---\")\n", + " print(d.get(\"content_txt_fr\", \"[No text]\"))\n", + " print(d.get(\"content_txt_de\", \"[No text]\"))" + ] + }, + { + "cell_type": "markdown", + "id": "a37c1ea1-6427-40a0-a3e2-101f0804481b", + "metadata": {}, + "source": [ + "#### Chunk Embeddings - In-corpus queries\n" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "id": "2eb1d5ad-b9e6-42f0-9a07-8e38f9c9c2c6", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Got 5 Solr document(s)\n", + "\n" + ] + } + ], + "source": [ + "chunk = (\n", + " \"Le congrès international s'est tenu à Paris pour discuter des avancées scientifiques de la décennie. \"\n", + " \"Des chercheurs venus de nombreux pays ont présenté leurs travaux les plus récents dans les domaines de la physique, \"\n", + " \"de la biologie et des sciences sociales. \"\n", + " \"Les débats ont mis en lumière les progrès réalisés grâce à la collaboration entre institutions européennes et américaines, \"\n", + " \"ainsi que les défis à venir pour une recherche plus ouverte et interdisciplinaire. \"\n", + " \"La rencontre s’est conclue par l’adoption d’une résolution encourageant la diffusion libre des connaissances scientifiques.\")\n", + "\n", + "result = impresso.experiments.execute(\n", + " experiment_id=\"subdoc-embeddings\",\n", + " body={\n", + " \"solrPayload\": {\n", + " \"query\": f\"content_txt_fr:({chunk}) AND type_s:c\",\n", + " \"limit\": 5,\n", + " \"params\": {\"hl\": False}\n", + " }\n", + " }\n", + ")\n", + "\n", + "docs = result[\"solrResponse\"][\"response\"][\"docs\"]\n", + "print(f\"✅ Got {len(docs)} Solr document(s)\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "id": "9d949cbb-3422-435a-8e7e-1816a0ae76b9", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "--- Result 0 ---\n", + "et leurs gouvernements respectifs. '.. \".'•••En outre, la nouvelle convention accorde la franchise de port pour la correspondance drdniaire des institutions nationales ayant un caractère scientifique et d' intérêt général ; ainsi qu' aux congrès scientifiques sud-américains composés de la majorité des pays de ce continent.Cette sage disposition constitue pour les sciences un bel encouragement et elle contribuera à répandre avec plus de facilité sur les immenses territoires de l' Amérique du Sud les progrès dus aux- efforts du génie humain.D' autre pari, le congrès postal dont nous analysons les travaux n' a pas blié les services rendus jpar la presse dans le domaine de l' éducation - des peuples.Il a cru devoir également favoriser la diffusion des idées, dans le louable désir d' accélérer - l' avènement de la turité - politique des citoyens.C' est pourquoi la franchise de.port est accordée aux éditeurs de journaux quotidiens et de publications périodiques sud-américains pour les exemplaires jusqu' au nombre de deux échangés par.ces éditeurs entre eux., '.Les Américains, qu' ils soient de souche latine ou anglo-saxonne, ont décidément une manière charmante et bien à eux d' apprêter toutes choses.C.-.\n", + "[No text]\n", + "--- Result 1 ---\n", + "Ces deux domaines nécessitent plus que jamais une collaboration au niveau international.Le séjour de jeunes scientifiques et artistes dans d' autres pays industrialisés d' Europe et d' outre-mer permet un transfert et un échange féconds des connaissances.Aucun scientifique, aucun artiste ne peut de nos jours, s' il veut œuvrer à l' avant-garde de sa discipline ou de son art, ignorer les impulsions venant de l' étranger.La manière la plus efficace d' apprendre à connaître une culture et un patrimoine étrangers est, comme toujours, de séjourner dans le pays concerné.Les contacts avec d' autres pays ont toujours été très importants pour la Suisse.Bien que de nombreux établissements de formation supérieure de l' ensemble des pays maintenant en général leurs portes ouvertes aux étrangers, des bourses gouvernementales, dans certains pays, représentent la seule possibilité pour des Suisses d' avoir accès à leurs hautes écoles ou académies.\n", + "[No text]\n", + "--- Result 2 ---\n", + "Il a écrit dix mémoires ou livres ins- pirés par ses recherches expérimentales.Enfin, il a fourni dix-huit mémoires de physique, publiés dans la Revue scientifique, sur l' évolution de la matière.De plus, Gustave Le Bon a donné à la Bibliothèque de philosophie scientifique, fondée et dirigée par lui, cinq volumes, sur L' Evolution de la Matière, La Psychologie de VEducation, La Psychologie politique, Les Opinions et les Croyances, et, tout dernièrement.\n", + "[No text]\n", + "--- Result 3 ---\n", + "Elle a été intellectualiste.Or, la philosophie nouvelle débute par un # critique, subtile et puisante, de La nature des vérités scientifiques, et de la valeur de l' intelligence comme faculté de connaître.Selon Bergson, le domaine propre de l' intelligence, et aussi bien de la science, œuvre de l' intelligenoe, ce n' est pas le vivant, c' est le matériel, l' inorganique. «JA > monde de la vie et de l' âme, en ce qu' il a d' essentiel et de profond, relève non plus de la connaissance scientifique mais d' uno connaissance spéciale, qui est proprement la connaissance philosophique ou métaphysique », ou encore l' intuition ( 2 ).IJrrgson mtfirme tloac la priorité sur 1 activité réfléchie d' une activité plus obscure et plus riche, qui consiste dans la faculté de sympathiser avec les choses, et qui est.très proche peut-être de l' amour.Cette indépendance de la science et de la connaissance profonde ou intuitive, l' une se bornant à prendre contact avec les choses, 1 autre visant à les comprendre, est d' une extrême conséquence.Le champ de la science, ce n' est donc plus le vrai mais l' utile : son rôle c' est de renforcer notre action sur la nature extérieure, d' aider à la satisfaction de nos besoins matériels, et non point de nous faire connaître la vérité.Pour un philosophe wmme Blondel, oomme Le Roy, \" comme Henri Poincaré, la science elle-même est quelque chose d' infiniment moins réel, eu somme, que la philosophie ; c' est une sorte de symbolisme, arbitraire en son principe, suivi et lié dans son développement continu, et qui d' ailleurs n a point à se préoccuper d' expliquer le fond des choses, mais seulement, de constituer un système de relations cohérentes, en vue de certaines fins pratiques.Devant elle, la loi se présente comme une traduction commode du monde extérieur et, non plus comme un décret qui, ravissant à l' homme sa liberté l, prétend guider sa conduite.L apologétique moderne reçoit de cette philosophie une forme nouvelle.\n", + "[No text]\n", + "--- Result 4 ---\n", + "L' idé.en est due au citoyen Lavigue, de Bordeaux, secrétaire de la- « Fédération nationale des Syndicats de France ».Le 20 juillet 1889, au Congrès socialiste intermfci mal de Paris, il proposa la résolution suivante : « Il sera organisé une grande manifestation internationale à dr.te fixe, de manière que, dans tous les pays et dans toutes les grandes villes à la fois, le même jour _ convenu, les travailleurs mettent les pouvoirs publics en demeure de réduire légalement à huit heures la jovrnée de travail et d' appliquer les _ atit es résolutions du Congrès international de Paris. »Ce texte fut adopté d' enthousiasme.\n", + "[No text]\n" + ] + } + ], + "source": [ + "for i, d in enumerate(docs):\n", + " print(f\"--- Result {i} ---\")\n", + " print(d.get(\"content_txt_fr\", \"[No text]\"))\n", + " print(d.get(\"content_txt_de\", \"[No text]\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 86, + "id": "2311f073-e4c7-48cc-9ed1-d595c8c73e60", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[-0.039117645, 0.062711135, -0.060027212]" + ] + }, + "execution_count": 86, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "embedding = docs[0]['gte_multi_v768']\n", + "\n", + "embedding[:3]" + ] + }, + { + "cell_type": "code", + "execution_count": 87, + "id": "18b92de3-53b7-4e59-adca-5abf30d0a777", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Got 3 Solr document(s)\n", + "\n" ] } ], "source": [ - "for doc in result['solrResponse']['response']['docs']:\n", - " print(doc.get('content_txt_fr', '')[:200]) # first 200 characters of the document content" + "result = impresso.experiments.execute(\n", + " experiment_id=\"subdoc-embeddings\",\n", + " body={\n", + " \"solrPayload\": {\n", + " \"query\": \"{!knn f=gte_multi_v768 topK=3}\" + str(embedding),\n", + " \"limit\": 3,\n", + " \"params\": {\n", + " \"fq\": \"type_s:c\", # type_s:c restricts search to chunks! (c=chunk)\n", + " # \"fl\": \"id,score,content_txt_fr,ci_id_s\", -- add these later if you want to return only specific fields\n", + " # for now let's return everything\n", + " \"hl\": False\n", + " }\n", + " }\n", + " }\n", + ")\n", + "\n", + "docs = result[\"solrResponse\"][\"response\"][\"docs\"]\n", + "print(f\"✅ Got {len(docs)} Solr document(s)\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "id": "96684e03-a785-4c6f-bb2d-443db7566995", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "--- Result 0 ---\n", + "[No text]\n", + "gskosten Briefbeföid «.auf die eigentliche Beförderung zwei Drittel aber auf den den Schalterdienst « nd Bestelldienst fallen.Der große Gedanke macht « Schule : er iibec » schritt die Grenzen des Landes ud n versuchte sich auch auf internationalem Boden.Nebst dem Weltpostverein, der uns im Jahre 1875 das internationale Einheitsporto für Briefe brachte, entstanden eine Anzahl Sonderpost der.eine, die Hauptsächlich den Zweck hatten, d « Inlandsporto der Vertragsstaaten auch auf ihren ieg « nseitiaen Auhenveikehr auszudehnen.Selbst uor dem Meere macht « das Einheitsporlo « ich » Halt.Im Jahre 1898 Antrag führte England auf den seines Abgeordneten Henniker-Heaton im Verkehr mit seinen Kolonien das Penny.Porto ein ; Deutschland folgte diesem Beispiele 1N99. Seit 19N8 19l ) 9 verkehrt Großbritannien unö seit auch Deutschland mit den Vereinigten Staaten von Amerika zum Inlandssahe.Begehren Auch in der Schweiz wurden schon laut, öfters die ähnliche Abkommen mit unsern Nachbarstaaten forderten ; nackig doch hart- wehren sich maßgebenden unsere Verwalfundstellen stets dagegen.Immer wird von ihnen nur darauf hingewiesen, baß die nung Ausdeh.\n", + "--- Result 1 ---\n", + "[No text]\n", + "treffenden Branche.Im allgemeinen kann man sagen, batz bei de « gegenwärtigen Sachlage die Ve » arbeltun « de » südamerikanischen Markte » durch entsprechen » vorgebildete Meisende und Spe » zialagenten der Vermittlung durch allgemein « Exporthäuser bei weitem vorzuziehen ist.Frei » lich ist es bei der kleinen Zahl wirklich zuverlässige, und vertrauenswürdiger Agentuifiimen auf den südamerikanischen Plätzen nicht leicht, einen « « igneten Vertreter zu finden und die Fabriken weiden sich im allgemeinen dazu entschließen müssen, neben einer angemessene n Provision einen festen Bureau zufchiih zu leisten und wohlassortierte Muster giati » zu stellen.In der Papierbranche und den ihr verwandten Geschäftszweigen hat der Gedanke, direkt zu exportleren, gleichfalls gemacht.\n", + "--- Result 2 ---\n", + "[No text]\n", + "Am August 24. hat Präsident Taft die Pauamakaual'Vorlage unterzeichnet und ihr ein Memorandum an den Kongreß beigegeben.In Veröffentlichung gelangten dieser zur Denk » schrift führt Taft aus, die Vorlage sei eine der segensreichsten, die je erlassen worden.Er sehe trotz den gegen sie erhobenen Einwendungen lei » nen Grund, bie unbedingt notwendigen Vorkeh » runge » zu verschieben, damit die Welt ihre Vor » bereitungen für die Eröffnung des Panamakanals treffen lönne, wissend, unter welchen Bedingungen dies geschehen werde.Eingehend be » ' handelt das Memorandum die verschiedenen Einwendungen, am ausführlichsten den eng « wegen der Verletzung t » es lischen Protest Ha y. » P a u n c e f o t e'V e r t r a g e s. Dieser Abschnitt darf deshalb eine besonderes Interesse beanspruchen, weil einiges hier zum erstenmal Mls der Protestnote Englands bekannt wird.Taft kommt zu dem Schluß, dah die Vereinigten Staaten üurch den genannten Vertrag sich nicht des Nechts begeben hätten, ihre Schiffe abgaben » frei zu machen oder die Zölle zurüszugeben.Ar « tikel 3 des Vertrages, um den der Streit sich drehe, sei eine Erklärung der Vereinigten Staa » ten, daß der Kanal neutral bleiben solle und bah die Vereinigten Staaten alle Staaten gleich behandeln wollten, sofern diese die Verträgst « « binnimaen erfüllen.DerArtikel stelle mit andern Worten eine Meistbegünstigungsklausel dar, deren Unterlage nicht die Vorteile seien, die die Vereinigten Staaten eigenen ihren Landeskin » öern gewähren, sondern bie Behandlung, die sie andern Nationen angedeihen liehen.Der eng » tische Einspruch würde zu der absurden Schluß » folgerung leiten, daß die Regierung, die den Kn » nal baut, unterhält und verteidigt, sich um das Recht verkürzt sieht, ihren eigene » Handel nach eigenem Ermessen zu führen, während alle an » dern Nationen in dem Wettbewerb mit Amerika dieses Recht uneingeschränkt besitzen, nämlich das Recht der Iollrü'ckvergütungen.Taft protestiert gegen diese Ansicht, als ob die Vereinigten Staaten auf das Recht, ihren Handel zu regeln, verzichten sollten, ein Recht, auf das wederGroßbritannien noch eine andere den Kanal durch » fahrende Nation verzichtet hätte oder verzichten Wolle.Die hat der Nill wie dem sie beglei » renden Memorandum Tafts sofort einen Kom » mental gewidmet, der an Deutlichkeit nichts zu wünschen übrig Iaht und die Stimmung in Eng « land klar illustriert.DaS Londoner Weltblatt bemerkt zunächst, daß der Wortlaut des Pa » namakanalgesetzes sowie der Denkschrift des Präsidenten vorliege, noch wicht baß aber, wenn die telegraphischen Berichte nur richtig einigermaßen seien, das Gesetz mit dem offenkundigen Hin » des Hay-Pauncefote-Vertrages unvereinbar sei.Der letzte Vorschlag des Präsidenten sei etwas Neues in der Geschichte deS Völker » « Feuilleton.\n" + ] + } + ], + "source": [ + "for i, d in enumerate(docs):\n", + " print(f\"--- Result {i} ---\")\n", + " print(d.get(\"content_txt_fr\", \"[No text]\"))\n", + " print(d.get(\"content_txt_de\", \"[No text]\"))" ] }, { @@ -328,7 +3817,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 92, "id": "686d1e8f", "metadata": {}, "outputs": [ @@ -357,7 +3846,7 @@ " '_root_']" ] }, - "execution_count": 18, + "execution_count": 92, "metadata": {}, "output_type": "execute_result" } @@ -367,7 +3856,7 @@ " experiment_id=\"entity-profiles\",\n", " body={\n", " \"solrPayload\": {\n", - " \"query\": \"wiki_url_s:*Albert*Einstein*\",\n", + " \"query\": \"wiki_url_s:*Simone*de*Beauvoir*\",\n", " \"limit\": 1,\n", " \"params\": {\n", " \"hl\": False\n", @@ -375,13 +3864,48 @@ " }\n", " }\n", ")\n", - "einstein_doc = result['solrResponse']['response']['docs'][0]\n", - "list(einstein_doc.keys())" + "entity_doc = result['solrResponse']['response']['docs'][0]\n", + "\n", + "list(entity_doc.keys())" + ] + }, + { + "cell_type": "code", + "execution_count": 93, + "id": "28d1b084-853b-4e61-8a65-0d61146eb522", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['political philosopher',\n", + " 'journalist',\n", + " 'novelist',\n", + " 'autobiographer',\n", + " 'essayist',\n", + " 'political activist',\n", + " 'diarist',\n", + " 'women letter writer',\n", + " 'philosopher',\n", + " 'literary critic',\n", + " 'writer',\n", + " 'author',\n", + " 'feminist',\n", + " 'philosophy teacher']" + ] + }, + "execution_count": 93, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "entity_doc['wkd_occupations_ss']" ] }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 98, "id": "677ca42e", "metadata": {}, "outputs": [ @@ -389,9 +3913,11 @@ "name": "stdout", "output_type": "stream", "text": [ - "https://de.wikipedia.org/wiki/Carl_Einstein\n", - "https://de.wikipedia.org/wiki/Hendrik_Antoon_Lorentz\n", - "https://fr.wikipedia.org/wiki/Hippolyte_Fizeau\n" + "https://de.wikipedia.org/wiki/Simone_de_Beauvoir\n", + "https://fr.wikipedia.org/wiki/Hélène_de_Beauvoir\n", + "https://fr.wikipedia.org/wiki/Jean_Beauvoir\n", + "https://fr.wikipedia.org/wiki/Simone_Chalon\n", + "https://fr.wikipedia.org/wiki/Sylvia_Earle\n" ] } ], @@ -400,11 +3926,11 @@ " experiment_id=\"entity-profiles\",\n", " body={\n", " \"solrPayload\": {\n", - " \"query\": \"{!knn f=entity_mixed_emb_v768 topK=3}\"+str(einstein_doc['entity_mixed_emb_v768']),\n", + " \"query\": \"{!knn f=entity_mixed_emb_v768 topK=5}\" + str(entity_doc['entity_mixed_emb_v768']),\n", " \"filter\": [\n", " f\"-id:{einstein_doc['id']}\" # exclude target entity itself\n", " ],\n", - " \"limit\": 3,\n", + " \"limit\": 5,\n", " \"params\": {\n", " \"hl\": False\n", " }\n", @@ -419,7 +3945,7 @@ ], "metadata": { "kernelspec": { - "display_name": "impresso-py3.13 (3.13.7)", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -433,7 +3959,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.13.7" + "version": "3.11.10" } }, "nbformat": 4, From f2334f29957c423e8bea44be3a5df70f28f82440 Mon Sep 17 00:00:00 2001 From: Emanuela Boros Date: Wed, 29 Oct 2025 10:46:09 +0100 Subject: [PATCH 2/7] experiments notebook documented --- examples/notebooks/experiments.ipynb | 2423 +------------------------- 1 file changed, 44 insertions(+), 2379 deletions(-) diff --git a/examples/notebooks/experiments.ipynb b/examples/notebooks/experiments.ipynb index 357bf17..01a19d3 100644 --- a/examples/notebooks/experiments.ipynb +++ b/examples/notebooks/experiments.ipynb @@ -42,7 +42,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 1, "id": "babd8f0e-b1fd-4000-8bd4-386fbdf83da8", "metadata": {}, "outputs": [ @@ -71,7 +71,7 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 2, "id": "509603ee", "metadata": {}, "outputs": [ @@ -129,10 +129,10 @@ "" ], "text/plain": [ - "" + "" ] }, - "execution_count": 33, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -161,7 +161,7 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 3, "id": "5ef16862-23ad-4447-be29-49be71260333", "metadata": {}, "outputs": [ @@ -194,7 +194,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 4, "id": "df2b9dab", "metadata": {}, "outputs": [ @@ -223,7 +223,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 5, "id": "73fafa3f-9b12-491c-9f8a-c56736c48bd6", "metadata": { "scrolled": true @@ -1009,7 +1009,7 @@ " '_root_': 'indeplux-1912-06-14-a-i0001-s-27'}" ] }, - "execution_count": 36, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -1020,7 +1020,7 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 6, "id": "ca0d7ea8-7545-449a-aad3-e95d2ea33fb2", "metadata": {}, "outputs": [ @@ -1030,7 +1030,7 @@ "'Mais c’ est une question qui ne peut se régler en congrès internationaux et c’ est pourquoi le pays cjui ne présente pas une natalité suffisante sera étranglé, ce qui ne sera d’ ailleurs qu’ une avanc'" ] }, - "execution_count": 37, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -1049,7 +1049,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 7, "id": "0b4d2ef2-bfc1-4941-aba4-ec6ab7002310", "metadata": {}, "outputs": [ @@ -1059,7 +1059,7 @@ "[-0.081427164, 0.064372316, -0.045108054]" ] }, - "execution_count": 38, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -1072,7 +1072,7 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 8, "id": "f85b2817", "metadata": {}, "outputs": [], @@ -1082,7 +1082,7 @@ }, { "cell_type": "code", - "execution_count": 75, + "execution_count": 9, "id": "b97665a0", "metadata": {}, "outputs": [ @@ -1118,2352 +1118,17 @@ }, { "cell_type": "code", - "execution_count": 76, + "execution_count": 25, "id": "09ec22e2-8605-47fe-ae74-10371ffb8453", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "[{'id': 'GDL-1912-01-25-a-i0001-s-65',\n", - " 'type_s': 's',\n", - " 'content_txt_fr': \"En outre, la nouvelle convention accorde la franchise de port pour la correspondance drdniaire des institutions nationales ayant un caractère scientifique et d' intérêt général ; ainsi qu' aux congrès scientifiques sud-américains composés de la majorité des pays de ce continent.\",\n", - " 'ci_id_s': 'GDL-1912-01-25-a-i0001',\n", - " 'gte_multi_v768': [-0.051615752,\n", - " 0.05201664,\n", - " -0.049590472,\n", - " 0.03735869,\n", - " -0.05054572,\n", - " 0.0066682235,\n", - " 0.017149948,\n", - " 0.029176751,\n", - " 0.1008355,\n", - " -0.06555545,\n", - " 0.02282818,\n", - " -0.004284408,\n", - " 0.06918294,\n", - " 0.05266427,\n", - " -0.1323649,\n", - " 0.07952411,\n", - " 0.10921394,\n", - " 0.061787345,\n", - " 0.026983595,\n", - " -0.03820048,\n", - " 0.06531311,\n", - " 0.04358564,\n", - " -0.022574957,\n", - " -0.055607993,\n", - " -0.017880114,\n", - " 0.08863045,\n", - " 0.075027466,\n", - " 0.00598791,\n", - " -0.029623808,\n", - " 0.04483322,\n", - " -0.07739359,\n", - " 0.013161964,\n", - " 0.06096676,\n", - " 0.07653891,\n", - " 0.020618537,\n", - " 0.066804744,\n", - " 0.003295666,\n", - " 0.018790608,\n", - " -0.019829411,\n", - " 0.063828565,\n", - " -0.009492278,\n", - " 0.012099424,\n", - " -0.03702587,\n", - " 0.06130341,\n", - " -0.044647235,\n", - " 0.064631134,\n", - " -0.042960476,\n", - " 0.031465385,\n", - " 0.016465947,\n", - " 0.0739859,\n", - " -0.029774092,\n", - " 0.0396995,\n", - " 0.0077195545,\n", - " 0.0735613,\n", - " 0.016696824,\n", - " 0.05187279,\n", - " -0.03604686,\n", - " 0.03519577,\n", - " 0.08680929,\n", - " -0.018466,\n", - " 0.06026104,\n", - " -0.0032086065,\n", - " -0.008187865,\n", - " 0.037388857,\n", - " 0.06477858,\n", - " -0.04534802,\n", - " 0.015970873,\n", - " -0.043672122,\n", - " 0.051750317,\n", - " -0.000932299,\n", - " -0.072477564,\n", - " 0.024720566,\n", - " 0.022310376,\n", - " 0.014357782,\n", - " -0.049257237,\n", - " 0.076934956,\n", - " -0.0076242355,\n", - " 0.008307401,\n", - " -0.010138375,\n", - " 0.037909407,\n", - " 0.0040230146,\n", - " -0.048211735,\n", - " -0.00052228814,\n", - " -0.024161067,\n", - " -0.016096635,\n", - " 0.0059468257,\n", - " -0.013075567,\n", - " 0.02069194,\n", - " 0.008249857,\n", - " 0.017511917,\n", - " 0.11059983,\n", - " 0.07871855,\n", - " -0.035136413,\n", - " -0.0054236567,\n", - " 0.028771387,\n", - " 0.036885332,\n", - " -0.042637754,\n", - " -0.009461706,\n", - " 0.04435888,\n", - " 0.017993977,\n", - " -0.03013215,\n", - " 0.032274075,\n", - " 0.035419617,\n", - " -0.06720839,\n", - " 0.0127287125,\n", - " 0.021468151,\n", - " 0.01510161,\n", - " 0.01637483,\n", - " -0.020533161,\n", - " -0.015646867,\n", - " -0.008983932,\n", - " -0.021627953,\n", - " -0.051015522,\n", - " 0.011945374,\n", - " -0.025561973,\n", - " 0.009892356,\n", - " 0.036670934,\n", - " -0.010536299,\n", - " 0.06747981,\n", - " 0.070237994,\n", - " -0.014428563,\n", - " 5.314551e-05,\n", - " -0.0674437,\n", - " 0.0013509023,\n", - " -0.119708546,\n", - " 0.035609808,\n", - " 0.023638168,\n", - " -0.046389047,\n", - " -0.0034867222,\n", - " -0.029822085,\n", - " 0.07264101,\n", - " -0.01248558,\n", - " -0.028398713,\n", - " -0.0034294068,\n", - " 0.0460668,\n", - " -0.043848146,\n", - " -0.011794878,\n", - " 0.021345017,\n", - " 0.0004661887,\n", - " 0.0034974788,\n", - " -0.03950107,\n", - " 0.0319008,\n", - " -0.03189924,\n", - " 0.051244847,\n", - " 0.0053909104,\n", - " -0.0077845873,\n", - " 0.037087847,\n", - " -0.07880855,\n", - " 0.024216598,\n", - " -0.020771429,\n", - " -0.0034421848,\n", - " 0.03145833,\n", - " -0.03342526,\n", - " -0.0037502071,\n", - " 0.020279478,\n", - " -0.010619189,\n", - " 0.017508822,\n", - " 0.059134666,\n", - " -0.021911254,\n", - " -0.045016967,\n", - " 0.040860157,\n", - " 0.04547328,\n", - " -0.017553328,\n", - " -0.023265574,\n", - " -0.03242842,\n", - " -0.013684788,\n", - " -0.011217002,\n", - " 0.016167177,\n", - " 0.06555258,\n", - " 0.010355337,\n", - " -0.06031211,\n", - " 0.032271758,\n", - " 0.030278115,\n", - " -0.038748793,\n", - " -0.035640717,\n", - " 0.05087693,\n", - " -0.023270492,\n", - " 0.027843362,\n", - " -0.054154206,\n", - " 0.06533668,\n", - " 0.04797114,\n", - " -0.0014793635,\n", - " -0.084928125,\n", - " -0.083849825,\n", - " -0.0061715883,\n", - " -0.014985692,\n", - " 0.0099981455,\n", - " -0.020289913,\n", - " -0.029778289,\n", - " 0.02260849,\n", - " -0.034603857,\n", - " -0.045593247,\n", - " -0.06415319,\n", - " 0.01738982,\n", - " -0.037352238,\n", - " -0.040368818,\n", - " 0.010010408,\n", - " 0.02707113,\n", - " -0.011680812,\n", - " -0.018027654,\n", - " 0.024377994,\n", - " 0.023387276,\n", - " -0.016730819,\n", - " 0.03560658,\n", - " 0.035914868,\n", - " -0.026126612,\n", - " -0.0061368523,\n", - " -0.011479972,\n", - " 0.0100026075,\n", - " 0.010929561,\n", - " 0.02099457,\n", - " -0.01906599,\n", - " 0.034597356,\n", - " 0.018949876,\n", - " 0.02747244,\n", - " -0.022969738,\n", - " -0.04813395,\n", - " -0.018661518,\n", - " -0.013425553,\n", - " -0.01429428,\n", - " -0.016052166,\n", - " -0.0072409627,\n", - " -0.010831443,\n", - " -0.011443295,\n", - " -0.0062117577,\n", - " 0.010178804,\n", - " -0.025773551,\n", - " 0.0010628019,\n", - " 0.009158145,\n", - " 0.03361166,\n", - " -0.016050575,\n", - " -0.0063553024,\n", - " -0.021517018,\n", - " -0.018869486,\n", - " 0.0022371148,\n", - " 0.008782952,\n", - " 0.015057313,\n", - " 0.048567265,\n", - " 0.035071198,\n", - " 0.014853163,\n", - " 0.020440245,\n", - " -0.0015704749,\n", - " 0.030761616,\n", - " 0.043883644,\n", - " 0.021389458,\n", - " 0.078753635,\n", - " -0.05006035,\n", - " -0.03267201,\n", - " -0.032212876,\n", - " -0.0015862249,\n", - " -0.009999616,\n", - " 0.015572369,\n", - " 0.005264143,\n", - " 0.019296315,\n", - " -0.06321326,\n", - " -0.015364111,\n", - " -0.008891938,\n", - " 0.0379309,\n", - " 0.07026531,\n", - " -0.025643144,\n", - " -0.037246145,\n", - " 0.0011652529,\n", - " -0.0041922727,\n", - " -0.066680424,\n", - " 0.022525202,\n", - " -0.087653115,\n", - " -0.00046321764,\n", - " 0.035173774,\n", - " -0.058347158,\n", - " -0.045212146,\n", - " -0.017727235,\n", - " 0.05030683,\n", - " -0.022088924,\n", - " 0.012100173,\n", - " -0.03692086,\n", - " -0.028271051,\n", - " -0.04061667,\n", - " -0.0269407,\n", - " -0.002010739,\n", - " 0.029786596,\n", - " 0.05351522,\n", - " 0.0003377929,\n", - " -0.031983797,\n", - " 0.020290243,\n", - " -0.037977874,\n", - " 0.013784169,\n", - " 0.044094533,\n", - " -0.014481101,\n", - " -0.012275437,\n", - " 0.03201192,\n", - " -0.027549576,\n", - " -0.033356402,\n", - " 0.025171299,\n", - " -0.0014885762,\n", - " 0.03243893,\n", - " -0.032851167,\n", - " -0.06013589,\n", - " -0.030034231,\n", - " 0.032897018,\n", - " -0.020489698,\n", - " -0.047812004,\n", - " -0.00567419,\n", - " 0.05399784,\n", - " 0.019845333,\n", - " 0.0014612435,\n", - " -0.03538008,\n", - " -0.025331436,\n", - " -0.05707104,\n", - " -0.05330605,\n", - " 0.038766127,\n", - " 0.007857965,\n", - " -0.0053681857,\n", - " -0.03586249,\n", - " -0.01866089,\n", - " 0.01579822,\n", - " 0.03613172,\n", - " 0.037488427,\n", - " -0.019580815,\n", - " -0.07559065,\n", - " 0.00030233548,\n", - " 0.0071869846,\n", - " 0.042891856,\n", - " -0.011900373,\n", - " 0.019067554,\n", - " 0.008102365,\n", - " -0.036573064,\n", - " 0.03383329,\n", - " 0.006066424,\n", - " -0.016126228,\n", - " -0.0052911234,\n", - " 0.0048901057,\n", - " 0.01314156,\n", - " 0.025600754,\n", - " -0.074093334,\n", - " 0.027695276,\n", - " 0.006291198,\n", - " 0.02625118,\n", - " -0.020182537,\n", - " 0.042970575,\n", - " 0.015145495,\n", - " 0.050841894,\n", - " 0.029992417,\n", - " -0.037823357,\n", - " 0.02162169,\n", - " -0.0004975816,\n", - " 0.015324387,\n", - " 0.09757915,\n", - " 0.0071103387,\n", - " 0.026537541,\n", - " -0.02470101,\n", - " -0.008112973,\n", - " 0.065199085,\n", - " 0.024691427,\n", - " 0.012051806,\n", - " 0.01553574,\n", - " -0.00042199486,\n", - " -0.02054252,\n", - " 0.052470174,\n", - " -0.009581189,\n", - " 0.102331154,\n", - " 0.011244549,\n", - " -0.026529666,\n", - " 0.021703994,\n", - " 0.029255254,\n", - " -0.033522166,\n", - " -0.0033538584,\n", - " -0.0070442623,\n", - " -0.016324533,\n", - " 0.037732713,\n", - " -0.032576457,\n", - " -0.040807158,\n", - " -0.008757524,\n", - " -0.053028453,\n", - " 0.06443136,\n", - " -0.028360164,\n", - " 0.00793884,\n", - " 0.00080381194,\n", - " 0.016525649,\n", - " 0.011521507,\n", - " -0.037688028,\n", - " 0.014363011,\n", - " 0.048708167,\n", - " 0.023563437,\n", - " 0.019654522,\n", - " 0.026665622,\n", - " 0.024950488,\n", - " -0.01698889,\n", - " -0.029528854,\n", - " 0.0040981895,\n", - " -0.010146843,\n", - " 0.030675,\n", - " -0.029994393,\n", - " -0.009192765,\n", - " 0.03446682,\n", - " 0.034251526,\n", - " 0.03600614,\n", - " 0.0659266,\n", - " 0.020939728,\n", - " -0.001578855,\n", - " -0.031628225,\n", - " -0.010255595,\n", - " -0.018427707,\n", - " 0.023688035,\n", - " 0.03347112,\n", - " 0.028568842,\n", - " -0.017189782,\n", - " -0.00047363061,\n", - " -0.036223978,\n", - " -0.009172375,\n", - " -0.0018126044,\n", - " -0.007849988,\n", - " -0.0013811503,\n", - " 0.021117633,\n", - " -0.055400144,\n", - " 0.05436228,\n", - " -0.018043539,\n", - " 0.022044713,\n", - " 0.039080553,\n", - " 0.12751073,\n", - " -0.04444646,\n", - " 0.010775138,\n", - " 0.03844832,\n", - " -0.0030779832,\n", - " -0.042486113,\n", - " -0.019147042,\n", - " 0.016373958,\n", - " -0.015320426,\n", - " 0.06634088,\n", - " -0.0046683224,\n", - " 0.043384567,\n", - " -0.027876206,\n", - " 0.036001135,\n", - " -0.008584567,\n", - " -0.040407035,\n", - " -0.008925749,\n", - " 0.02888885,\n", - " 0.013540931,\n", - " 0.0050304076,\n", - " 0.02160886,\n", - " 0.04516263,\n", - " 0.009231834,\n", - " -0.033741664,\n", - " 0.00065888575,\n", - " -0.0710957,\n", - " 1.5987278e-05,\n", - " -0.0052919546,\n", - " -0.041170474,\n", - " 0.050878037,\n", - " -0.054500967,\n", - " 0.0232423,\n", - " -0.02436334,\n", - " 0.01782443,\n", - " -0.038947564,\n", - " -0.022209924,\n", - " 0.025447844,\n", - " 0.010800896,\n", - " -0.035247203,\n", - " 0.03191183,\n", - " 0.018120473,\n", - " -0.035099182,\n", - " 0.017186083,\n", - " -0.0054308176,\n", - " -0.02025944,\n", - " -0.043736085,\n", - " 0.044223715,\n", - " -0.0030811294,\n", - " 0.009738583,\n", - " 0.019276137,\n", - " -0.031711154,\n", - " 0.014869599,\n", - " -0.022863857,\n", - " 2.836195e-05,\n", - " -0.008967894,\n", - " 0.00046533902,\n", - " -0.0027317973,\n", - " 0.03320151,\n", - " 0.033403296,\n", - " 0.009921753,\n", - " 0.053694297,\n", - " 0.012582393,\n", - " 0.0022654077,\n", - " 0.016692635,\n", - " -0.004928809,\n", - " -0.024572613,\n", - " -0.041334826,\n", - " 0.013191648,\n", - " -0.045705587,\n", - " -0.071707435,\n", - " -0.0023595307,\n", - " 0.03667151,\n", - " 0.01801371,\n", - " 0.05604066,\n", - " 0.007484501,\n", - " -0.023895055,\n", - " 0.026544055,\n", - " 0.06848308,\n", - " -0.03402582,\n", - " -0.014590876,\n", - " 0.018667994,\n", - " -0.02413681,\n", - " -0.0557327,\n", - " -0.00880924,\n", - " 0.0075870627,\n", - " 0.045969486,\n", - " 0.0067385123,\n", - " -0.05023535,\n", - " 0.081836514,\n", - " -0.06026567,\n", - " 0.03204409,\n", - " -0.050728705,\n", - " -0.04784797,\n", - " -0.04638116,\n", - " -0.040952284,\n", - " -0.02447224,\n", - " -0.032183353,\n", - " -0.013256539,\n", - " 0.019123388,\n", - " -0.042831633,\n", - " -0.062628426,\n", - " 0.06995105,\n", - " 0.0218928,\n", - " -0.026224487,\n", - " -0.03296055,\n", - " 0.02423779,\n", - " 0.0125061,\n", - " -0.014371768,\n", - " -0.022743473,\n", - " -0.0012859623,\n", - " -0.0035610357,\n", - " -0.044091284,\n", - " 0.047810983,\n", - " 0.019562677,\n", - " 0.013388826,\n", - " -0.00012975158,\n", - " -0.05017465,\n", - " -0.004343915,\n", - " -0.020601902,\n", - " 0.025956646,\n", - " 0.023021614,\n", - " 0.009083039,\n", - " -0.064484395,\n", - " 0.021771988,\n", - " -0.017145673,\n", - " 0.036277615,\n", - " -0.008368489,\n", - " -0.0021986258,\n", - " 0.060611546,\n", - " -0.043499753,\n", - " -0.036393628,\n", - " 0.02459264,\n", - " 0.021183167,\n", - " 0.040052474,\n", - " 0.048911143,\n", - " 0.0018307558,\n", - " -0.0062714755,\n", - " -0.046554904,\n", - " 0.016214289,\n", - " -0.03842713,\n", - " 0.003178687,\n", - " 0.011152627,\n", - " -0.022851048,\n", - " -0.039629385,\n", - " 0.0016096554,\n", - " 0.041658763,\n", - " 0.05001978,\n", - " -0.029240588,\n", - " 0.002162648,\n", - " 0.032104794,\n", - " -0.00022503638,\n", - " 0.016997557,\n", - " -0.035969168,\n", - " -0.048558243,\n", - " 0.023870349,\n", - " -0.059834648,\n", - " -0.021206262,\n", - " -0.016442128,\n", - " -0.031565625,\n", - " -0.018789502,\n", - " -0.04246573,\n", - " 0.00845029,\n", - " 0.012945361,\n", - " -0.0007564261,\n", - " 0.005647039,\n", - " 0.051532418,\n", - " 0.012688975,\n", - " 0.0040408326,\n", - " -0.032260336,\n", - " 0.03656761,\n", - " -0.07194418,\n", - " -0.041979972,\n", - " 0.010066044,\n", - " -0.027413668,\n", - " 0.027000293,\n", - " -0.028258733,\n", - " 0.0447612,\n", - " 0.013929022,\n", - " -0.0039374125,\n", - " 0.011760333,\n", - " 0.017692896,\n", - " 0.026930073,\n", - " 0.008479024,\n", - " -0.02473566,\n", - " 0.008381769,\n", - " -0.025436137,\n", - " 0.026188018,\n", - " 0.029156292,\n", - " 0.023755766,\n", - " -0.07497574,\n", - " -0.016339287,\n", - " -0.0013905796,\n", - " -0.043203693,\n", - " -0.0062072696,\n", - " 0.031943817,\n", - " 0.022805497,\n", - " -0.079688415,\n", - " 0.009569476,\n", - " -0.041275863,\n", - " -0.051839773,\n", - " 0.02049438,\n", - " -0.03258229,\n", - " -0.02952811,\n", - " -0.040654197,\n", - " 0.0760365,\n", - " 0.003759511,\n", - " -0.007872424,\n", - " -0.0041186046,\n", - " -0.03549695,\n", - " -0.07696831,\n", - " -0.04416744,\n", - " -0.036314365,\n", - " -0.048074644,\n", - " -0.042366136,\n", - " -0.009535127,\n", - " -0.01230737,\n", - " -0.03673247,\n", - " 0.03096408,\n", - " -0.040810056,\n", - " 0.0038574976,\n", - " 0.02200458,\n", - " 0.002395138,\n", - " -0.030524805,\n", - " 0.009790649,\n", - " 0.009715365,\n", - " 0.04182122,\n", - " 0.030246397,\n", - " -0.03775568,\n", - " 0.007914768,\n", - " -0.009346499,\n", - " -0.03662862,\n", - " 0.014972676,\n", - " 0.03378411,\n", - " -0.048841577,\n", - " -0.0080238925,\n", - " -0.023907293,\n", - " -0.044986926,\n", - " -0.016466996,\n", - " -0.036266856,\n", - " -0.032230325,\n", - " -0.010940956,\n", - " 0.04471258,\n", - " 0.009344574,\n", - " -0.03611318,\n", - " 0.12816468,\n", - " 0.022074984,\n", - " -0.043523904,\n", - " 0.006402435,\n", - " 0.028247586,\n", - " 0.019084008,\n", - " 0.035987437,\n", - " 0.022977242,\n", - " 0.07773884,\n", - " -0.020035839,\n", - " -0.07158775,\n", - " -0.0010573787,\n", - " -0.02083184,\n", - " 0.03020219,\n", - " 0.026788305,\n", - " -0.043400384,\n", - " 0.026104674,\n", - " 0.00999582,\n", - " 0.01626253,\n", - " -0.053540748,\n", - " -0.028148673,\n", - " 0.02778322,\n", - " -0.07438462,\n", - " -0.0025628132,\n", - " -0.024457622,\n", - " 0.02585507,\n", - " 0.01657554,\n", - " 0.011961711,\n", - " 0.022417044,\n", - " -0.01039462,\n", - " 0.007850443,\n", - " -0.016122239,\n", - " 0.011302527,\n", - " -0.0024541456,\n", - " 0.010531964,\n", - " -0.0055627287,\n", - " 0.0050982395,\n", - " 0.01852299,\n", - " -0.0124726575,\n", - " -0.015639938,\n", - " 0.045438852,\n", - " 0.03466487,\n", - " 0.008506276,\n", - " 0.015463898,\n", - " -0.008730163,\n", - " -0.008596632,\n", - " 0.0006707985,\n", - " 0.024400542,\n", - " 0.04579195,\n", - " 0.0027356267,\n", - " -0.007052415,\n", - " 0.06489034,\n", - " -0.027781425,\n", - " -0.0048737847,\n", - " 0.0025846898,\n", - " -0.0011396497,\n", - " -0.061632667,\n", - " 0.053359985,\n", - " -0.053128414,\n", - " 0.0036842236,\n", - " -0.034069344,\n", - " 0.012609027,\n", - " 0.0021951955,\n", - " 0.007911464,\n", - " -0.027023457,\n", - " 0.070675686,\n", - " -0.030743489,\n", - " 0.024965337,\n", - " 0.040861886,\n", - " 0.015782895,\n", - " -0.03373192,\n", - " 0.0023073703,\n", - " 0.0075245793,\n", - " 0.009876064,\n", - " 0.019852692,\n", - " -0.03305989,\n", - " -0.00039043516,\n", - " 0.03612556,\n", - " 0.028484007,\n", - " -0.040667344,\n", - " -0.007624668,\n", - " 0.030401532,\n", - " 0.047515836,\n", - " 0.025457151,\n", - " 0.032370426,\n", - " -0.040960114,\n", - " 0.029548109,\n", - " -0.015358702,\n", - " -0.051161453,\n", - " 0.01867429,\n", - " -0.005633792,\n", - " -0.0164262,\n", - " 0.052699134,\n", - " -0.021055548,\n", - " 0.045519546,\n", - " -0.039158266,\n", - " -0.045086816,\n", - " 0.013899674,\n", - " 0.012462053,\n", - " 0.045320608,\n", - " -0.010657815,\n", - " 0.0069521023,\n", - " -0.032610457,\n", - " -0.05496854,\n", - " 0.019171735,\n", - " 0.06461833],\n", - " 'lg_s': 'fr',\n", - " '_version_': 1843523311144796160,\n", - " '_root_': 'GDL-1912-01-25-a-i0001-s-65'},\n", - " {'id': 'GDL-1912-01-25-a-i0001-s-29',\n", - " 'type_s': 's',\n", - " 'content_txt_fr': 'Certaines dispositions insérées dans la nouvelle convention sud-américaine ont sans contredit une portée autre que simplement postale.',\n", - " 'ci_id_s': 'GDL-1912-01-25-a-i0001',\n", - " 'gte_multi_v768': [-0.07270199,\n", - " 0.061392926,\n", - " -0.025212321,\n", - " 0.04842686,\n", - " -0.030294813,\n", - " 0.035191197,\n", - " -0.04358981,\n", - " 0.0038277104,\n", - " 0.085862525,\n", - " -0.04771203,\n", - " 0.01479704,\n", - " -0.013705449,\n", - " 0.027255017,\n", - " -0.00032638258,\n", - " -0.0535441,\n", - " 0.06433969,\n", - " 0.0870326,\n", - " 0.01321177,\n", - " 0.08558132,\n", - " 0.0005348483,\n", - " 0.08191568,\n", - " 0.025292994,\n", - " -0.039012924,\n", - " -0.020857098,\n", - " -0.0076694754,\n", - " 0.045723043,\n", - " 0.07569519,\n", - " -0.0071770684,\n", - " -0.07248518,\n", - " 0.016248405,\n", - " -0.09151575,\n", - " -0.028681815,\n", - " 0.0987924,\n", - " 0.011966113,\n", - " 0.056395438,\n", - " 0.011246147,\n", - " -0.032881655,\n", - " 0.016141465,\n", - " 0.03489068,\n", - " 0.015539575,\n", - " 0.048718866,\n", - " 0.05077653,\n", - " 0.0058326954,\n", - " -0.0015803308,\n", - " -0.016934639,\n", - " 0.031860374,\n", - " -0.039273117,\n", - " 0.050979868,\n", - " -0.012123115,\n", - " 0.029870547,\n", - " -0.044660818,\n", - " 0.010465813,\n", - " 0.020638926,\n", - " 0.008092918,\n", - " 0.03601937,\n", - " 0.032458056,\n", - " -0.105812624,\n", - " 0.014728648,\n", - " 0.07972083,\n", - " -0.0049583884,\n", - " 0.009220236,\n", - " -0.0022415437,\n", - " -0.05352581,\n", - " 0.03732541,\n", - " 0.06655571,\n", - " 0.020603223,\n", - " 0.033650473,\n", - " -0.047396556,\n", - " 0.07408663,\n", - " 0.005310279,\n", - " -0.051956754,\n", - " 0.004049972,\n", - " 0.0051678894,\n", - " 0.03096769,\n", - " -0.02968057,\n", - " 0.04748652,\n", - " -0.0059046075,\n", - " 0.03897846,\n", - " 0.031265296,\n", - " 0.010408316,\n", - " -0.05055094,\n", - " 0.0017630998,\n", - " 0.038844217,\n", - " -0.02534684,\n", - " -0.029771607,\n", - " -0.06687983,\n", - " -0.020020494,\n", - " 0.031773075,\n", - " 0.021087222,\n", - " -0.015565782,\n", - " 0.085392,\n", - " 0.064326406,\n", - " -0.018500494,\n", - " -0.006530731,\n", - " 0.047252536,\n", - " 0.0863165,\n", - " -0.035916302,\n", - " 0.023582164,\n", - " 0.08987791,\n", - " -0.017850174,\n", - " -0.075919226,\n", - " 0.038317222,\n", - " 0.020746242,\n", - " -0.054941483,\n", - " 0.032969326,\n", - " -0.02528709,\n", - " 0.02404556,\n", - " -0.018367948,\n", - " -0.044298112,\n", - " -0.032287084,\n", - " -0.042414498,\n", - " -0.05339762,\n", - " -0.06956395,\n", - " -0.028822873,\n", - " 0.0083979,\n", - " 0.023924638,\n", - " 0.028597783,\n", - " -0.06879725,\n", - " 0.048090484,\n", - " 0.059585776,\n", - " -0.016346283,\n", - " -0.005510254,\n", - " -0.064414516,\n", - " -0.024313008,\n", - " -0.053362753,\n", - " -0.001980558,\n", - " -0.0058990843,\n", - " -0.07435654,\n", - " 0.00804072,\n", - " 0.012742878,\n", - " 0.06795072,\n", - " 0.00017609757,\n", - " 0.046402264,\n", - " -0.01044538,\n", - " 0.0058663357,\n", - " -0.0451728,\n", - " 0.046612617,\n", - " 0.041145798,\n", - " 0.02295734,\n", - " -0.026006384,\n", - " -0.067377806,\n", - " -0.011408535,\n", - " -0.050212357,\n", - " 0.028501505,\n", - " 0.004271683,\n", - " 0.007336688,\n", - " -0.0026925632,\n", - " -0.07369538,\n", - " 0.05921478,\n", - " 0.008519318,\n", - " -0.005634117,\n", - " 0.029249141,\n", - " -0.022305908,\n", - " -0.017682286,\n", - " 0.024379397,\n", - " -0.04734149,\n", - " -0.015316724,\n", - " 0.075583965,\n", - " 0.010154082,\n", - " -0.03282173,\n", - " 0.029942155,\n", - " 0.038819402,\n", - " 0.02441589,\n", - " -0.01055037,\n", - " -0.05625257,\n", - " -0.014384699,\n", - " -0.024380013,\n", - " 0.03882333,\n", - " 0.07295608,\n", - " -0.013830722,\n", - " -0.060851064,\n", - " 0.017682424,\n", - " 0.020742288,\n", - " -0.027935466,\n", - " -0.027335946,\n", - " -0.03009823,\n", - " 0.0014494349,\n", - " 0.057282817,\n", - " -0.06258341,\n", - " 0.04828263,\n", - " -0.013397304,\n", - " 0.033821102,\n", - " -0.09812918,\n", - " -0.02750474,\n", - " 0.060738374,\n", - " 0.018970234,\n", - " 0.0059009683,\n", - " -0.0040276865,\n", - " 0.03282429,\n", - " -0.008775085,\n", - " -0.017078843,\n", - " -0.015721487,\n", - " -0.06266291,\n", - " 0.015922893,\n", - " 0.0022748741,\n", - " -0.020557612,\n", - " -0.012811559,\n", - " 0.045904584,\n", - " -0.034843687,\n", - " -0.030370345,\n", - " -0.0035589614,\n", - " 0.019647267,\n", - " 0.040806767,\n", - " 0.037716903,\n", - " 0.0047070934,\n", - " -0.051038835,\n", - " 0.0053223954,\n", - " -0.0051626465,\n", - " 0.004518503,\n", - " -0.009002026,\n", - " 0.015349202,\n", - " -0.037259646,\n", - " 0.03074719,\n", - " 0.027023815,\n", - " 0.010073604,\n", - " 0.015536163,\n", - " -0.055264518,\n", - " -0.018882325,\n", - " 0.004607553,\n", - " -0.009193998,\n", - " -0.011627999,\n", - " 0.004904914,\n", - " -0.014073629,\n", - " -0.02542841,\n", - " -0.04605124,\n", - " 0.021779291,\n", - " -0.01680755,\n", - " 0.021296147,\n", - " -0.015360311,\n", - " 0.009882392,\n", - " 0.030316025,\n", - " 0.024714394,\n", - " 0.009831074,\n", - " -0.04055002,\n", - " -0.01691468,\n", - " 0.027992884,\n", - " 0.0024250648,\n", - " 0.03726409,\n", - " -0.009548601,\n", - " 0.056431785,\n", - " 0.017792832,\n", - " -0.017150199,\n", - " 0.04523755,\n", - " 0.030130023,\n", - " -0.009212122,\n", - " 0.05134318,\n", - " 0.0040995083,\n", - " -0.064521655,\n", - " -0.04092778,\n", - " -0.019817367,\n", - " -0.0012400284,\n", - " 0.019691017,\n", - " 0.038562704,\n", - " 0.03977343,\n", - " -0.048494305,\n", - " -0.025027953,\n", - " -0.01927051,\n", - " -0.0015091224,\n", - " 0.0696117,\n", - " -0.0492665,\n", - " -0.014430027,\n", - " -0.01078952,\n", - " -0.046552517,\n", - " -0.045800272,\n", - " 0.0245287,\n", - " -0.10945937,\n", - " -0.010983787,\n", - " 0.03558626,\n", - " -0.029388275,\n", - " -0.04510395,\n", - " -0.025314933,\n", - " 0.10240726,\n", - " -0.05566458,\n", - " 0.0903111,\n", - " -0.03553116,\n", - " -0.0063938363,\n", - " -0.0601896,\n", - " -0.06805767,\n", - " 0.040524926,\n", - " 0.025733506,\n", - " -0.002730592,\n", - " -0.026106093,\n", - " -0.047036238,\n", - " -0.027412934,\n", - " -0.05640688,\n", - " 0.036764037,\n", - " 0.03826593,\n", - " -0.01328978,\n", - " -0.006152576,\n", - " 0.08365534,\n", - " 0.023071205,\n", - " 0.0014393347,\n", - " 0.0002518021,\n", - " 0.021357318,\n", - " 0.019425025,\n", - " -0.04351827,\n", - " -0.06667988,\n", - " 0.011600028,\n", - " 0.04470064,\n", - " -0.0285423,\n", - " -0.028581293,\n", - " -0.031258833,\n", - " 0.062057465,\n", - " 0.031595234,\n", - " -0.02372499,\n", - " -0.007897933,\n", - " -0.020015046,\n", - " -0.040688634,\n", - " -0.024159312,\n", - " 0.0125957085,\n", - " 0.012913835,\n", - " 0.015382748,\n", - " -0.029148549,\n", - " -0.041560646,\n", - " 0.026299838,\n", - " 0.02667616,\n", - " 0.05904669,\n", - " -0.009734496,\n", - " -0.082171634,\n", - " -0.04897272,\n", - " -0.047273252,\n", - " 0.022053381,\n", - " -0.0102919405,\n", - " 0.005035418,\n", - " -0.016853224,\n", - " -0.026692236,\n", - " 0.03900197,\n", - " 0.025118783,\n", - " -0.0038165401,\n", - " -0.018625524,\n", - " -0.00093953725,\n", - " 0.026513776,\n", - " 0.0202959,\n", - " -0.051877648,\n", - " 0.017134102,\n", - " 0.03131422,\n", - " 0.039644957,\n", - " -0.042753182,\n", - " 0.027404577,\n", - " 0.010539758,\n", - " 0.024265798,\n", - " 0.02560602,\n", - " -0.07568404,\n", - " 0.019028177,\n", - " 0.039411005,\n", - " -0.02820163,\n", - " 0.071243376,\n", - " -0.002909679,\n", - " 0.011384622,\n", - " -0.034663226,\n", - " -0.02491936,\n", - " 0.010973925,\n", - " 0.013038525,\n", - " -0.016868137,\n", - " 0.013330403,\n", - " 0.03721675,\n", - " -0.0116533525,\n", - " 0.0660362,\n", - " 0.013076732,\n", - " 0.037467334,\n", - " 0.0040909257,\n", - " -0.0125504825,\n", - " 0.00473948,\n", - " 0.009605131,\n", - " 2.7920505e-05,\n", - " 0.00083843997,\n", - " -0.022395005,\n", - " 0.006482994,\n", - " 0.028651446,\n", - " -0.011440122,\n", - " 0.005150829,\n", - " 0.010992955,\n", - " -0.053774204,\n", - " 0.11025878,\n", - " 0.008214591,\n", - " 0.034915168,\n", - " 0.006734031,\n", - " 0.071137644,\n", - " 0.0007473978,\n", - " 0.0030503934,\n", - " 0.008741315,\n", - " 0.023735357,\n", - " 0.013980801,\n", - " 0.013177856,\n", - " 0.029854268,\n", - " 0.046920385,\n", - " -0.02960938,\n", - " -0.04344335,\n", - " -0.008770195,\n", - " 0.005110264,\n", - " -0.015945116,\n", - " -0.035708215,\n", - " 0.013059246,\n", - " 0.01971841,\n", - " 0.011224667,\n", - " 0.027569195,\n", - " 0.06170682,\n", - " 0.019510545,\n", - " 0.0022188863,\n", - " 0.024892962,\n", - " 0.006424488,\n", - " -0.0036090515,\n", - " 0.06568954,\n", - " -0.015655326,\n", - " 0.010469926,\n", - " -0.061592937,\n", - " 0.0043100817,\n", - " -0.033313517,\n", - " 0.036303308,\n", - " -0.003472825,\n", - " -0.02342374,\n", - " -0.025014998,\n", - " 0.022471495,\n", - " -0.07994925,\n", - " -0.01872536,\n", - " -0.021303372,\n", - " 0.024599075,\n", - " 0.027735086,\n", - " 0.14824665,\n", - " -0.0456896,\n", - " 0.014300305,\n", - " 0.03312556,\n", - " 0.03444799,\n", - " -0.06708897,\n", - " 0.004239601,\n", - " -0.032036383,\n", - " 0.023367295,\n", - " -0.025686061,\n", - " 0.0024110237,\n", - " 0.06124078,\n", - " -0.024855759,\n", - " 0.031359654,\n", - " -0.01875005,\n", - " -0.03340488,\n", - " -0.015814602,\n", - " 0.0094120195,\n", - " -0.043995585,\n", - " -0.008542137,\n", - " 0.024300741,\n", - " 0.032288793,\n", - " -0.0013875114,\n", - " -0.019588053,\n", - " 0.027253438,\n", - " -0.05210502,\n", - " -0.037047185,\n", - " 0.018336035,\n", - " -0.0027175995,\n", - " 0.024460023,\n", - " 0.008385286,\n", - " 0.029484948,\n", - " 0.0021098796,\n", - " 0.003140468,\n", - " -0.031146022,\n", - " -0.043809425,\n", - " 0.02471543,\n", - " 0.005733976,\n", - " -0.023251366,\n", - " 0.02595415,\n", - " 0.017859114,\n", - " -0.050796635,\n", - " 0.00884804,\n", - " -0.031136574,\n", - " -0.0036211,\n", - " -0.006290338,\n", - " 0.044331662,\n", - " 0.007915345,\n", - " 0.004572766,\n", - " 0.0010671264,\n", - " -0.00742993,\n", - " 0.027130095,\n", - " 0.03541406,\n", - " 0.011719837,\n", - " -0.010450444,\n", - " -0.032455105,\n", - " -0.016336476,\n", - " 0.04392271,\n", - " 0.0049837725,\n", - " 0.03821958,\n", - " 0.059777457,\n", - " 0.009425316,\n", - " 0.0038634965,\n", - " 0.0069770236,\n", - " -0.0537969,\n", - " -0.048112135,\n", - " 0.00559711,\n", - " 0.027470322,\n", - " -0.044646565,\n", - " -0.07993179,\n", - " -0.004917187,\n", - " 0.021244297,\n", - " 0.014287805,\n", - " 0.036142014,\n", - " 0.0012862032,\n", - " -0.024688799,\n", - " 0.0015671145,\n", - " 0.057700757,\n", - " 0.049819138,\n", - " -0.058502465,\n", - " 0.085045055,\n", - " -0.020705963,\n", - " -0.044569276,\n", - " -0.00055668765,\n", - " -0.009131631,\n", - " 0.020861601,\n", - " 0.042134173,\n", - " 0.0129635045,\n", - " 0.06391071,\n", - " -0.049672384,\n", - " 0.046645127,\n", - " -0.027140489,\n", - " 0.008348439,\n", - " -0.044767596,\n", - " -0.016717143,\n", - " -0.035923313,\n", - " -0.022292176,\n", - " -0.007542445,\n", - " -0.008969496,\n", - " -0.012061755,\n", - " -0.050202377,\n", - " 0.053905237,\n", - " 0.026214758,\n", - " -0.023733322,\n", - " -0.04358869,\n", - " 0.02482057,\n", - " -0.009394614,\n", - " -0.07469014,\n", - " -0.013170866,\n", - " 0.029578324,\n", - " 0.029162087,\n", - " -0.028436398,\n", - " 0.04165277,\n", - " 0.03568401,\n", - " 0.0064282557,\n", - " 0.026195243,\n", - " -0.029818274,\n", - " 0.025353555,\n", - " -0.02269713,\n", - " 0.025988407,\n", - " 0.02207938,\n", - " -0.014281597,\n", - " -0.04456545,\n", - " 0.0014086809,\n", - " -0.037698995,\n", - " 0.023803687,\n", - " -0.0027242722,\n", - " -0.01891849,\n", - " 0.047836542,\n", - " -0.054733414,\n", - " -0.022390537,\n", - " -0.0010643392,\n", - " 0.012789696,\n", - " 0.080227524,\n", - " 0.03610625,\n", - " 0.019415706,\n", - " -0.046773214,\n", - " -0.048641067,\n", - " 0.013460196,\n", - " -0.011560607,\n", - " -0.0033479875,\n", - " 0.042660754,\n", - " -0.05731083,\n", - " -0.028147407,\n", - " 0.008415662,\n", - " 0.012787636,\n", - " 0.0024955238,\n", - " -0.005875471,\n", - " -0.013299467,\n", - " 0.037166175,\n", - " 0.0057459143,\n", - " 0.012639692,\n", - " -0.015172107,\n", - " -0.022445424,\n", - " 0.017624319,\n", - " 0.009638046,\n", - " -0.046090864,\n", - " -0.0060588145,\n", - " -0.043850314,\n", - " 0.03045057,\n", - " -0.038855284,\n", - " 0.045535054,\n", - " 0.009548614,\n", - " 0.011949054,\n", - " -0.007565267,\n", - " 0.029646084,\n", - " -0.023318162,\n", - " -0.0033369183,\n", - " -0.035498414,\n", - " 0.062240385,\n", - " -0.018729104,\n", - " -0.04776792,\n", - " 0.024890197,\n", - " -0.028041568,\n", - " 0.029823277,\n", - " -0.060630605,\n", - " 0.028923012,\n", - " 0.0063285865,\n", - " -0.020326551,\n", - " 0.023190375,\n", - " 0.022982161,\n", - " 0.016292645,\n", - " 0.03233532,\n", - " -0.031412743,\n", - " 0.034803633,\n", - " 0.041211806,\n", - " 0.026718382,\n", - " 0.028487919,\n", - " 0.0359467,\n", - " -0.06362591,\n", - " -0.030659683,\n", - " -0.01509082,\n", - " -0.020952778,\n", - " 0.011969293,\n", - " 0.023588603,\n", - " 0.022859022,\n", - " -0.092516154,\n", - " 0.013380597,\n", - " -0.034692783,\n", - " -0.026464676,\n", - " -0.03864589,\n", - " -0.0037144811,\n", - " -0.028045015,\n", - " -0.018442508,\n", - " 0.036016736,\n", - " 0.008804359,\n", - " -0.003898757,\n", - " -0.009917567,\n", - " -0.03118676,\n", - " -0.026093764,\n", - " -0.04284072,\n", - " -0.03664036,\n", - " -0.018243145,\n", - " -0.017400395,\n", - " -0.011264005,\n", - " -0.07358787,\n", - " -0.057193514,\n", - " 0.050511945,\n", - " -0.028301546,\n", - " -0.016631387,\n", - " 0.05484464,\n", - " 0.007213607,\n", - " -0.034849387,\n", - " 0.068434425,\n", - " 0.012187549,\n", - " 0.0073545114,\n", - " 0.038115777,\n", - " -0.019442376,\n", - " 0.0088192,\n", - " 0.02426156,\n", - " -0.025240779,\n", - " 0.015097276,\n", - " 0.02413101,\n", - " -0.060335062,\n", - " 0.013571056,\n", - " 0.013849029,\n", - " -0.029186107,\n", - " -0.006919429,\n", - " -0.04999688,\n", - " -0.01516865,\n", - " -0.033374574,\n", - " 0.050494786,\n", - " 0.0081956405,\n", - " -0.000781171,\n", - " 0.1156525,\n", - " -0.0032045883,\n", - " -0.04926413,\n", - " 0.021553678,\n", - " 0.011936843,\n", - " 0.044372372,\n", - " 0.06430836,\n", - " -0.057773627,\n", - " 0.039314836,\n", - " -0.02601572,\n", - " -0.0064663533,\n", - " -0.017725777,\n", - " -0.011883558,\n", - " 0.06588944,\n", - " 0.0027787196,\n", - " -0.0057342756,\n", - " -0.0026902868,\n", - " 0.010756356,\n", - " 0.006683054,\n", - " -0.011171504,\n", - " -0.010028028,\n", - " 0.03280309,\n", - " -0.03710007,\n", - " -0.00037581357,\n", - " -0.010274363,\n", - " 0.014990174,\n", - " 0.023026982,\n", - " 0.00462088,\n", - " -0.018528085,\n", - " 0.031811867,\n", - " -0.044433616,\n", - " 0.0017737364,\n", - " 0.020088844,\n", - " -0.0022534393,\n", - " -0.008028976,\n", - " -0.026758444,\n", - " -0.014790072,\n", - " -0.0027231018,\n", - " -0.024185179,\n", - " 0.022362713,\n", - " 0.037899133,\n", - " 0.023111207,\n", - " 0.035417896,\n", - " -0.014735656,\n", - " 0.014920871,\n", - " -0.018102232,\n", - " 0.003849651,\n", - " 0.014768346,\n", - " -0.0047033275,\n", - " 0.0076877363,\n", - " -0.08941378,\n", - " 0.04385689,\n", - " -0.02061675,\n", - " -0.0022157985,\n", - " 0.021340441,\n", - " 0.008795498,\n", - " -0.023795376,\n", - " 0.039326064,\n", - " -0.054837987,\n", - " -0.049411677,\n", - " -0.011908158,\n", - " 0.011915023,\n", - " 0.034715824,\n", - " 0.014839867,\n", - " -0.003681896,\n", - " 0.07058819,\n", - " -0.02855893,\n", - " 0.050516546,\n", - " -0.019206159,\n", - " 0.015897363,\n", - " -0.024837745,\n", - " 0.029461285,\n", - " 0.010113613,\n", - " 0.007867647,\n", - " 0.026553452,\n", - " -0.033507638,\n", - " -0.01779466,\n", - " 0.012894055,\n", - " 0.00731373,\n", - " -0.027972303,\n", - " 0.023625279,\n", - " 0.046873078,\n", - " -0.01835527,\n", - " 0.025398996,\n", - " -0.00947968,\n", - " 0.011787183,\n", - " 0.048391055,\n", - " 0.011638939,\n", - " 0.003961612,\n", - " 0.020612521,\n", - " 0.00543749,\n", - " 0.031116953,\n", - " 0.038547985,\n", - " -0.028023694,\n", - " 0.029720454,\n", - " -0.044062383,\n", - " -0.04660935,\n", - " 0.017674532,\n", - " -0.024052268,\n", - " 0.031557217,\n", - " 0.008316933,\n", - " 0.012430458,\n", - " -0.038235627,\n", - " -0.007937035,\n", - " -0.00097407197,\n", - " 0.031212503],\n", - " 'lg_s': 'fr',\n", - " '_version_': 1843523311038889984,\n", - " '_root_': 'GDL-1912-01-25-a-i0001-s-29'},\n", - " {'id': 'GDL-1912-01-25-a-i0001-s-70',\n", - " 'type_s': 's',\n", - " 'content_txt_fr': \"port est accordée aux éditeurs de journaux quotidiens et de publications périodiques sud-américains pour les exemplaires jusqu' au nombre de deux échangés par.\",\n", - " 'ci_id_s': 'GDL-1912-01-25-a-i0001',\n", - " 'gte_multi_v768': [-0.05680408,\n", - " 0.06387808,\n", - " -0.04856367,\n", - " 0.07558254,\n", - " -0.021889713,\n", - " 0.027441371,\n", - " 0.0015161067,\n", - " 0.027526896,\n", - " 0.070930585,\n", - " -0.058298152,\n", - " -0.011244095,\n", - " 0.047598463,\n", - " -0.030812727,\n", - " 0.04946567,\n", - " -0.1109161,\n", - " 0.075338885,\n", - " 0.09431828,\n", - " 0.065175645,\n", - " 0.048616614,\n", - " -0.015955964,\n", - " 0.060905457,\n", - " 0.004543543,\n", - " -0.015062949,\n", - " 0.027204664,\n", - " -0.012537254,\n", - " 0.109382056,\n", - " -0.0058181244,\n", - " -0.03267176,\n", - " -0.038578954,\n", - " 0.01801676,\n", - " -0.08267891,\n", - " -0.034785353,\n", - " 0.04281231,\n", - " 0.025842642,\n", - " 0.03903481,\n", - " 0.022392912,\n", - " -0.008075021,\n", - " -0.003958624,\n", - " 0.028308881,\n", - " 0.034027323,\n", - " -0.017764986,\n", - " -0.027231509,\n", - " -0.029520093,\n", - " 0.010817953,\n", - " 0.017693274,\n", - " 0.06503678,\n", - " -0.071917005,\n", - " 0.02230548,\n", - " 0.005966704,\n", - " 0.021682076,\n", - " -0.034017008,\n", - " 0.03497421,\n", - " 0.016124977,\n", - " 0.07258827,\n", - " 0.06323594,\n", - " 0.042673863,\n", - " -0.07751493,\n", - " 0.032996166,\n", - " 0.08310853,\n", - " -0.018388394,\n", - " 0.0512766,\n", - " -0.0032999113,\n", - " -0.025261564,\n", - " -0.008211472,\n", - " -0.006080969,\n", - " -0.030746382,\n", - " 0.018559372,\n", - " -0.026786452,\n", - " 0.10291751,\n", - " 0.044018302,\n", - " -0.044262085,\n", - " 0.03787636,\n", - " -0.023074595,\n", - " 0.03189656,\n", - " -0.022342745,\n", - " 0.02490987,\n", - " 0.0610374,\n", - " 0.05679413,\n", - " -0.015448033,\n", - " 0.04165428,\n", - " -0.041415293,\n", - " -0.04143148,\n", - " 0.033411153,\n", - " 0.027957879,\n", - " -0.05191326,\n", - " -0.021843795,\n", - " -0.0069933883,\n", - " 0.03257855,\n", - " -0.040802136,\n", - " -0.0039164457,\n", - " 0.051885936,\n", - " 0.08618492,\n", - " -0.00050581986,\n", - " -0.028928392,\n", - " 0.029504543,\n", - " 0.07240461,\n", - " -0.034900557,\n", - " 0.019995965,\n", - " 0.11230153,\n", - " 0.011365759,\n", - " -0.0054779435,\n", - " 0.018395215,\n", - " 0.02106766,\n", - " -0.03626866,\n", - " 0.028840657,\n", - " 0.019836048,\n", - " 0.022810984,\n", - " -0.0008726806,\n", - " 0.015734892,\n", - " -0.025800215,\n", - " -0.04126276,\n", - " -0.01494636,\n", - " -0.08921718,\n", - " -0.026337288,\n", - " 0.028740907,\n", - " -0.020959945,\n", - " 0.049158905,\n", - " -0.07213806,\n", - " 0.0026235483,\n", - " 0.047008693,\n", - " -0.03597703,\n", - " 0.012278491,\n", - " -0.078883186,\n", - " -0.022993986,\n", - " -0.07842844,\n", - " 0.006434972,\n", - " -0.047524337,\n", - " -0.06447543,\n", - " -0.0060534813,\n", - " -0.00589939,\n", - " 0.0760615,\n", - " 0.015441079,\n", - " 0.01964648,\n", - " 0.0011932348,\n", - " 0.06662931,\n", - " -0.023894684,\n", - " 0.017201254,\n", - " 0.07950517,\n", - " 0.035065234,\n", - " -0.032788448,\n", - " -0.05365816,\n", - " -0.005709627,\n", - " -0.052723065,\n", - " 0.05486205,\n", - " 0.023403581,\n", - " -0.014603613,\n", - " -0.021162527,\n", - " -0.052467994,\n", - " -0.03011303,\n", - " 0.0011532663,\n", - " 0.0003995073,\n", - " 0.0360547,\n", - " -0.011495599,\n", - " -0.04326665,\n", - " 0.024591248,\n", - " -0.03959948,\n", - " 0.03528982,\n", - " 0.06305916,\n", - " 0.017708087,\n", - " -0.017182063,\n", - " 0.0017088845,\n", - " 0.04461511,\n", - " -0.0039479155,\n", - " -0.043220203,\n", - " -0.047296237,\n", - " -0.010154965,\n", - " -0.028041942,\n", - " 0.0446806,\n", - " 0.03756078,\n", - " 0.020877628,\n", - " -0.07659133,\n", - " 0.03962669,\n", - " 0.029327717,\n", - " -0.015903363,\n", - " -0.035756286,\n", - " 0.04176602,\n", - " -0.02734469,\n", - " -0.0030521317,\n", - " -0.014741279,\n", - " 0.07573669,\n", - " 0.05783421,\n", - " -0.01144547,\n", - " -0.043425426,\n", - " -0.0663662,\n", - " 0.024635118,\n", - " -0.014225987,\n", - " 0.03249727,\n", - " 0.014217647,\n", - " 0.004667845,\n", - " 0.0358217,\n", - " -0.0242047,\n", - " -0.06522303,\n", - " -0.058395717,\n", - " 0.016197577,\n", - " -0.037792005,\n", - " -0.027401919,\n", - " -0.02850256,\n", - " 0.031710375,\n", - " -0.01611329,\n", - " 0.0021421046,\n", - " 0.012047816,\n", - " 0.020715512,\n", - " 0.039120678,\n", - " 0.021670764,\n", - " 0.0047489484,\n", - " -0.032356948,\n", - " 0.009116835,\n", - " -0.03439566,\n", - " -0.023327397,\n", - " -0.016594242,\n", - " 0.0014536829,\n", - " 0.009252665,\n", - " 0.0051945024,\n", - " -0.0043386198,\n", - " -0.040954057,\n", - " -0.020179464,\n", - " -0.05918961,\n", - " -0.0303645,\n", - " 0.037603993,\n", - " -0.008280048,\n", - " -0.0051193824,\n", - " -0.016355518,\n", - " -0.03947001,\n", - " -0.037388187,\n", - " -0.0053553856,\n", - " 0.020274382,\n", - " -0.019270543,\n", - " 0.022108195,\n", - " 0.0063307756,\n", - " -0.039626062,\n", - " 0.022539085,\n", - " -0.016099013,\n", - " 0.025176348,\n", - " 0.019320844,\n", - " -0.011700732,\n", - " 0.009495598,\n", - " 0.036385875,\n", - " 0.066322245,\n", - " -0.021529708,\n", - " 0.056870252,\n", - " 0.034732975,\n", - " -0.030924838,\n", - " 0.038632993,\n", - " 0.029679107,\n", - " -0.013694661,\n", - " 0.027893692,\n", - " -0.038053572,\n", - " -0.016527917,\n", - " -0.03648918,\n", - " 0.009421407,\n", - " -0.027731346,\n", - " 0.011813313,\n", - " 0.0126533,\n", - " 0.006421953,\n", - " -0.046381734,\n", - " -0.012230512,\n", - " 0.015225633,\n", - " -0.01651272,\n", - " 0.03236237,\n", - " -0.051103573,\n", - " -0.052263077,\n", - " 0.015807312,\n", - " -0.013421665,\n", - " -0.05319022,\n", - " 0.03754047,\n", - " -0.08575125,\n", - " 0.019848185,\n", - " 0.07780862,\n", - " -0.025172248,\n", - " -0.017809829,\n", - " 0.0054981536,\n", - " 0.02206488,\n", - " -0.0402048,\n", - " 0.05657433,\n", - " -0.052837722,\n", - " -0.03221729,\n", - " -0.017220937,\n", - " -0.020376498,\n", - " -0.01109481,\n", - " 0.015917942,\n", - " 0.025976157,\n", - " -0.023923505,\n", - " 0.01464813,\n", - " -0.018986428,\n", - " -0.011994399,\n", - " 0.0077301194,\n", - " 0.023208115,\n", - " -0.027664742,\n", - " -0.025231324,\n", - " 0.034364924,\n", - " -0.035596997,\n", - " -0.010281778,\n", - " -0.01776035,\n", - " -0.007292064,\n", - " 0.000418178,\n", - " -0.006930773,\n", - " -0.056325603,\n", - " 0.021520996,\n", - " 0.041496553,\n", - " 0.0063503096,\n", - " -0.036979865,\n", - " -0.03306839,\n", - " 0.03575481,\n", - " 0.039904743,\n", - " 0.036307413,\n", - " -0.044993307,\n", - " -0.022727903,\n", - " -0.017485218,\n", - " -0.085646205,\n", - " 0.017956333,\n", - " -0.0024675934,\n", - " 0.01523081,\n", - " -0.03383787,\n", - " -0.018295113,\n", - " 0.040419225,\n", - " 0.03375754,\n", - " -0.0061179134,\n", - " 0.02837869,\n", - " -0.06238745,\n", - " -0.0021848788,\n", - " -0.055100147,\n", - " 0.04505286,\n", - " 0.009902881,\n", - " -0.0011387669,\n", - " -0.0072524976,\n", - " -0.02486218,\n", - " 0.05738864,\n", - " 0.023359027,\n", - " -0.024014225,\n", - " -0.02835716,\n", - " 0.0062544495,\n", - " 0.017787637,\n", - " 0.01560684,\n", - " -0.05617647,\n", - " 0.012903993,\n", - " 0.044633143,\n", - " 0.026930042,\n", - " 0.010915518,\n", - " 0.05127232,\n", - " 0.029528333,\n", - " 0.024195252,\n", - " 0.053241197,\n", - " -0.0640872,\n", - " -0.03625579,\n", - " 0.007576901,\n", - " 0.010667519,\n", - " 0.09268224,\n", - " 0.011553675,\n", - " 0.01267877,\n", - " -0.02053662,\n", - " -0.009395332,\n", - " 0.008464381,\n", - " 0.020977568,\n", - " -0.01891739,\n", - " 0.032037094,\n", - " -0.020472875,\n", - " -0.010507396,\n", - " 0.07543627,\n", - " -0.038927633,\n", - " 0.064642675,\n", - " 0.043160703,\n", - " -0.0014504181,\n", - " -0.022373311,\n", - " 0.027925998,\n", - " 0.014306418,\n", - " -0.014883518,\n", - " -0.011328613,\n", - " 0.05313789,\n", - " 0.020786073,\n", - " -5.2853888e-05,\n", - " -0.002864547,\n", - " 0.020562628,\n", - " -0.019998584,\n", - " 0.10793451,\n", - " -0.04854008,\n", - " -0.03561407,\n", - " 0.00051874836,\n", - " -0.01930007,\n", - " 0.008874648,\n", - " 0.018628655,\n", - " 0.0150350705,\n", - " -0.023917707,\n", - " 0.031191936,\n", - " -0.018240798,\n", - " 0.02280116,\n", - " 0.031054737,\n", - " -0.043735705,\n", - " -0.049130388,\n", - " -0.020346304,\n", - " -0.044371933,\n", - " 0.0049108826,\n", - " -0.032801054,\n", - " 0.014804224,\n", - " 0.019464063,\n", - " -0.025238449,\n", - " -0.01920073,\n", - " 0.06630683,\n", - " 0.0370241,\n", - " 0.021422138,\n", - " 0.0237387,\n", - " 0.026918953,\n", - " 0.014984069,\n", - " 0.05003196,\n", - " -0.013169837,\n", - " 0.025115224,\n", - " -0.022145707,\n", - " 0.039328806,\n", - " -0.056289665,\n", - " 0.002686336,\n", - " -0.010678451,\n", - " 0.022610897,\n", - " -0.025488157,\n", - " 0.043593667,\n", - " -0.09402724,\n", - " 0.07852914,\n", - " -0.008758481,\n", - " 0.016202908,\n", - " 0.058471553,\n", - " 0.15999767,\n", - " -0.0017225927,\n", - " 0.0067002787,\n", - " 0.053081356,\n", - " 0.016023297,\n", - " -0.070710465,\n", - " -0.0056044315,\n", - " 0.036097743,\n", - " 0.037961904,\n", - " 0.0081612505,\n", - " -0.011321509,\n", - " 0.004900642,\n", - " -0.008063335,\n", - " 0.021463236,\n", - " -0.05130153,\n", - " -0.0652861,\n", - " -0.023450883,\n", - " 0.04997369,\n", - " 0.00024382243,\n", - " -0.04580109,\n", - " 0.021559305,\n", - " 0.024988277,\n", - " -0.013621296,\n", - " -0.0347862,\n", - " 0.030518003,\n", - " -0.018858507,\n", - " -0.050935045,\n", - " -0.0044698385,\n", - " 0.0074550062,\n", - " 0.049126945,\n", - " -0.038395636,\n", - " 0.047106765,\n", - " -0.027374133,\n", - " 0.016838936,\n", - " -0.030900508,\n", - " -0.0507253,\n", - " -0.00081984577,\n", - " 0.010674338,\n", - " -0.020206412,\n", - " 0.0151003385,\n", - " -0.042421304,\n", - " -0.027443845,\n", - " 0.0043962398,\n", - " -0.023046808,\n", - " -0.0029031036,\n", - " -0.044903956,\n", - " -0.022942783,\n", - " -0.0033205838,\n", - " 0.023103176,\n", - " 0.017453719,\n", - " -0.05724227,\n", - " 0.02223993,\n", - " 0.0045749834,\n", - " -0.0057145464,\n", - " 0.0055112913,\n", - " -0.022596361,\n", - " -0.049288895,\n", - " 0.052903038,\n", - " -0.032930087,\n", - " 0.044564545,\n", - " 0.037451547,\n", - " -0.008487822,\n", - " -0.00046948888,\n", - " 0.014867911,\n", - " -0.034751162,\n", - " -0.0073387115,\n", - " 0.026934503,\n", - " 0.014844265,\n", - " 0.008190351,\n", - " -0.045524325,\n", - " -0.0033880551,\n", - " 0.024464807,\n", - " 0.049926214,\n", - " 0.048998564,\n", - " 0.020574521,\n", - " 0.026498424,\n", - " 0.025967795,\n", - " 0.080135554,\n", - " -0.02498737,\n", - " -0.023838338,\n", - " 0.0589479,\n", - " -0.006773478,\n", - " -0.039905064,\n", - " -0.0062658098,\n", - " 0.045033496,\n", - " 0.06459868,\n", - " 0.002900991,\n", - " 0.0038800703,\n", - " 0.06322735,\n", - " 0.00029259123,\n", - " 0.025133284,\n", - " -0.048754428,\n", - " 0.00070420036,\n", - " -0.021258762,\n", - " -0.04107931,\n", - " -0.015941324,\n", - " -0.071368955,\n", - " -0.024546072,\n", - " -0.006689376,\n", - " 0.029536944,\n", - " -0.046778042,\n", - " 0.04152148,\n", - " 0.018942926,\n", - " -0.0067904987,\n", - " -0.044583526,\n", - " 0.017837103,\n", - " 0.04061375,\n", - " -0.052083123,\n", - " 0.0236291,\n", - " 0.01284286,\n", - " 0.0171025,\n", - " -0.02275749,\n", - " 0.033556618,\n", - " 0.004836787,\n", - " 0.03009814,\n", - " -0.052731037,\n", - " 0.013754754,\n", - " 0.053202175,\n", - " 0.010482435,\n", - " 0.04622099,\n", - " 0.019243684,\n", - " 5.367547e-05,\n", - " -0.011120939,\n", - " -0.02151325,\n", - " -0.04548332,\n", - " -0.022005042,\n", - " -0.018184977,\n", - " -0.036811054,\n", - " 0.019177958,\n", - " -0.06955333,\n", - " -0.0231974,\n", - " -0.028599884,\n", - " -0.027384752,\n", - " 0.033006314,\n", - " 0.011088715,\n", - " 0.0069307997,\n", - " -0.028356984,\n", - " -0.01316145,\n", - " 0.062719725,\n", - " 0.008206823,\n", - " -0.019569961,\n", - " -0.014994998,\n", - " -0.031228635,\n", - " -0.029914973,\n", - " 0.060132407,\n", - " 0.014801324,\n", - " 0.033433307,\n", - " 0.014585036,\n", - " -0.03210837,\n", - " -0.009049988,\n", - " -0.03037654,\n", - " 0.029199922,\n", - " -0.055459544,\n", - " -0.017411731,\n", - " 0.009728488,\n", - " -0.030245861,\n", - " -0.01829823,\n", - " -0.0068603996,\n", - " -0.017303465,\n", - " 0.010572903,\n", - " -0.02823631,\n", - " 0.051125452,\n", - " -0.032821577,\n", - " -0.007214039,\n", - " -0.024644949,\n", - " 0.027078621,\n", - " -0.03712036,\n", - " 0.0048836297,\n", - " -0.084682174,\n", - " 0.012341536,\n", - " -0.025374034,\n", - " -0.046953052,\n", - " 0.015795348,\n", - " -0.010103081,\n", - " 0.009278835,\n", - " -0.03617463,\n", - " 0.031759385,\n", - " 0.003919212,\n", - " 0.017071849,\n", - " -0.02655857,\n", - " 0.0028727693,\n", - " -0.008133552,\n", - " 0.0041895863,\n", - " -0.031180326,\n", - " 0.09085531,\n", - " 0.026876906,\n", - " 0.009257815,\n", - " 0.06918902,\n", - " 0.010982239,\n", - " -0.063372925,\n", - " -0.037140924,\n", - " 0.009987525,\n", - " -0.013391082,\n", - " 0.006153766,\n", - " 0.02854545,\n", - " 0.029123561,\n", - " -0.03588052,\n", - " 0.011743845,\n", - " -0.055579346,\n", - " -0.011289578,\n", - " -0.0044937357,\n", - " 0.0076637147,\n", - " -0.023567881,\n", - " 2.3369465e-05,\n", - " 0.025043108,\n", - " 0.021869775,\n", - " 0.054185614,\n", - " 0.006243622,\n", - " -0.054999202,\n", - " -0.055334296,\n", - " -0.0647816,\n", - " -0.01704009,\n", - " -0.053713467,\n", - " -0.04823133,\n", - " -0.014942541,\n", - " -0.05840356,\n", - " -0.012674364,\n", - " -0.003911387,\n", - " -0.050819866,\n", - " 0.00014474818,\n", - " 0.073844366,\n", - " 0.010522974,\n", - " 0.0015996089,\n", - " 0.008558171,\n", - " 0.010174858,\n", - " -0.028922917,\n", - " 0.029761026,\n", - " 0.010588534,\n", - " 0.017381694,\n", - " 0.009115375,\n", - " -0.018989211,\n", - " -0.003194415,\n", - " 0.013919865,\n", - " -0.03536051,\n", - " -0.032564633,\n", - " -0.026487092,\n", - " 0.020456523,\n", - " -0.0011054155,\n", - " -0.024419568,\n", - " -0.005077697,\n", - " -0.0095237745,\n", - " 0.084264286,\n", - " 0.022982834,\n", - " -0.014327535,\n", - " 0.15581359,\n", - " -0.023523292,\n", - " -0.0504727,\n", - " 0.031755354,\n", - " 0.015520586,\n", - " 0.05364135,\n", - " 0.058876373,\n", - " -0.02043425,\n", - " 0.048008807,\n", - " -0.0073660137,\n", - " -0.0052846954,\n", - " -0.024466448,\n", - " -0.014896462,\n", - " 0.010465434,\n", - " 0.0029648398,\n", - " -0.08468755,\n", - " -0.030296,\n", - " -0.0006499835,\n", - " -0.017287035,\n", - " -0.008246593,\n", - " -0.032095876,\n", - " 0.009795486,\n", - " -0.025566109,\n", - " 0.024589794,\n", - " -0.011263848,\n", - " 0.012535761,\n", - " 0.0023695156,\n", - " 0.007081577,\n", - " 0.014829279,\n", - " 0.017556475,\n", - " 0.0044162525,\n", - " 0.018217932,\n", - " 0.01936434,\n", - " -0.014689975,\n", - " -0.014862805,\n", - " -0.0339685,\n", - " 0.018071441,\n", - " -0.014117345,\n", - " 0.010728882,\n", - " 0.0010798945,\n", - " 0.0013677074,\n", - " -0.0035509395,\n", - " 0.0023138344,\n", - " -0.02207691,\n", - " 0.027792078,\n", - " -0.022042053,\n", - " 0.007442902,\n", - " -0.0030612324,\n", - " -0.009760814,\n", - " 0.037549023,\n", - " -0.02928992,\n", - " 0.05390074,\n", - " -0.019230692,\n", - " -0.012139241,\n", - " 0.001288939,\n", - " -0.011020472,\n", - " -0.043356016,\n", - " 0.05652876,\n", - " -0.042325146,\n", - " -0.013620406,\n", - " 0.0029760897,\n", - " 0.008271474,\n", - " 0.007846904,\n", - " 0.0011568316,\n", - " -0.013965066,\n", - " 0.047694013,\n", - " 0.013437404,\n", - " 0.034186125,\n", - " 0.013992624,\n", - " 0.042957436,\n", - " -0.017203378,\n", - " 0.061278712,\n", - " -0.005151349,\n", - " -0.02090346,\n", - " 0.014107725,\n", - " -4.5311303e-05,\n", - " -0.0111748595,\n", - " 0.01584758,\n", - " 0.01897466,\n", - " -0.03805934,\n", - " -0.022197109,\n", - " 0.03860355,\n", - " 0.0014635735,\n", - " 0.047886554,\n", - " 0.020262355,\n", - " 0.014944389,\n", - " 0.0116559435,\n", - " -0.01366922,\n", - " -0.046399254,\n", - " 0.011021824,\n", - " 0.00818818,\n", - " -0.013689622,\n", - " 0.030283738,\n", - " -0.0039186855,\n", - " 0.0021658074,\n", - " 0.056276754,\n", - " -0.023511963,\n", - " 0.0066836593,\n", - " -0.048657592,\n", - " 0.001489622,\n", - " 0.00783965,\n", - " -0.0446165,\n", - " -0.025651837,\n", - " 0.018622568,\n", - " 0.022268912,\n", - " 0.04480489],\n", - " 'lg_s': 'fr',\n", - " '_version_': 1843523311160524800,\n", - " '_root_': 'GDL-1912-01-25-a-i0001-s-70'}]" - ] - }, - "execution_count": 76, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ - "docs" + "# docs" ] }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 11, "id": "fcc6262c", "metadata": {}, "outputs": [ @@ -3472,14 +1137,14 @@ "output_type": "stream", "text": [ "--- Result 0 ---\n", - "En outre, la nouvelle convention accorde la franchise de port pour la correspondance drdniaire des institutions nationales ayant un caractère scientifique et d' intérêt général ; ainsi qu' aux congrès scientifiques sud-américains composés de la majorité des pays de ce continent.\n", + "Mais c’ est une question qui ne peut se régler en congrès internationaux et c’ est pourquoi le pays cjui ne présente pas une natalité suffisante sera étranglé, ce qui ne sera d’ ailleurs qu’ une avance sur son sui- cide.\n", "[No text]\n", "--- Result 1 ---\n", - "Certaines dispositions insérées dans la nouvelle convention sud-américaine ont sans contredit une portée autre que simplement postale.\n", "[No text]\n", + "weil sie nicht die ganze Nation in dem Parlament vertreten sehen wolle.\n", "--- Result 2 ---\n", - "port est accordée aux éditeurs de journaux quotidiens et de publications périodiques sud-américains pour les exemplaires jusqu' au nombre de deux échangés par.\n", - "[No text]\n" + "[No text]\n", + "Es steht zu hoffen, daß damit die vom Bundesrate getanen völlig gewesen Schritte nicht nutzlos sind, und daß in nicht allzu ferner Zeit doch noch eine solche internationale Konferenz sich mit dein Problem beschäftigen wird.\n" ] } ], @@ -3500,7 +1165,7 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 12, "id": "5e6798ed", "metadata": {}, "outputs": [ @@ -3510,7 +1175,7 @@ "'gte-768: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'" ] }, - "execution_count": 78, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -3524,7 +1189,7 @@ }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 13, "id": "0e58b62c", "metadata": {}, "outputs": [ @@ -3534,7 +1199,7 @@ "768" ] }, - "execution_count": 79, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -3553,7 +1218,7 @@ }, { "cell_type": "code", - "execution_count": 80, + "execution_count": 14, "id": "09489886-3fd4-498e-b534-298dda3ce96c", "metadata": {}, "outputs": [ @@ -3567,7 +1232,7 @@ " -0.08889304101467133]" ] }, - "execution_count": 80, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -3578,7 +1243,7 @@ }, { "cell_type": "code", - "execution_count": 81, + "execution_count": 15, "id": "27b47638", "metadata": {}, "outputs": [ @@ -3610,7 +1275,7 @@ }, { "cell_type": "code", - "execution_count": 82, + "execution_count": 16, "id": "4194268d", "metadata": {}, "outputs": [ @@ -3647,7 +1312,7 @@ }, { "cell_type": "code", - "execution_count": 83, + "execution_count": 17, "id": "2eb1d5ad-b9e6-42f0-9a07-8e38f9c9c2c6", "metadata": {}, "outputs": [ @@ -3686,7 +1351,7 @@ }, { "cell_type": "code", - "execution_count": 84, + "execution_count": 18, "id": "9d949cbb-3422-435a-8e7e-1816a0ae76b9", "metadata": {}, "outputs": [ @@ -3721,7 +1386,7 @@ }, { "cell_type": "code", - "execution_count": 86, + "execution_count": 19, "id": "2311f073-e4c7-48cc-9ed1-d595c8c73e60", "metadata": {}, "outputs": [ @@ -3731,7 +1396,7 @@ "[-0.039117645, 0.062711135, -0.060027212]" ] }, - "execution_count": 86, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } @@ -3744,7 +1409,7 @@ }, { "cell_type": "code", - "execution_count": 87, + "execution_count": 20, "id": "18b92de3-53b7-4e59-adca-5abf30d0a777", "metadata": {}, "outputs": [ @@ -3780,7 +1445,7 @@ }, { "cell_type": "code", - "execution_count": 88, + "execution_count": 21, "id": "96684e03-a785-4c6f-bb2d-443db7566995", "metadata": {}, "outputs": [ @@ -3817,7 +1482,7 @@ }, { "cell_type": "code", - "execution_count": 92, + "execution_count": 22, "id": "686d1e8f", "metadata": {}, "outputs": [ @@ -3846,7 +1511,7 @@ " '_root_']" ] }, - "execution_count": 92, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" } @@ -3871,7 +1536,7 @@ }, { "cell_type": "code", - "execution_count": 93, + "execution_count": 23, "id": "28d1b084-853b-4e61-8a65-0d61146eb522", "metadata": {}, "outputs": [ @@ -3894,7 +1559,7 @@ " 'philosophy teacher']" ] }, - "execution_count": 93, + "execution_count": 23, "metadata": {}, "output_type": "execute_result" } @@ -3905,7 +1570,7 @@ }, { "cell_type": "code", - "execution_count": 98, + "execution_count": 26, "id": "677ca42e", "metadata": {}, "outputs": [ @@ -3913,11 +1578,11 @@ "name": "stdout", "output_type": "stream", "text": [ - "https://de.wikipedia.org/wiki/Simone_de_Beauvoir\n", "https://fr.wikipedia.org/wiki/Hélène_de_Beauvoir\n", "https://fr.wikipedia.org/wiki/Jean_Beauvoir\n", "https://fr.wikipedia.org/wiki/Simone_Chalon\n", - "https://fr.wikipedia.org/wiki/Sylvia_Earle\n" + "https://fr.wikipedia.org/wiki/Sylvia_Earle\n", + "https://fr.wikipedia.org/wiki/Gustave_Simon\n" ] } ], @@ -3928,7 +1593,7 @@ " \"solrPayload\": {\n", " \"query\": \"{!knn f=entity_mixed_emb_v768 topK=5}\" + str(entity_doc['entity_mixed_emb_v768']),\n", " \"filter\": [\n", - " f\"-id:{einstein_doc['id']}\" # exclude target entity itself\n", + " f\"-id:{entity_doc['id']}\" # exclude target entity itself\n", " ],\n", " \"limit\": 5,\n", " \"params\": {\n", From fa9e247821713eb2dd198f7f300341e275f50aaf Mon Sep 17 00:00:00 2001 From: Emanuela Boros Date: Wed, 29 Oct 2025 10:49:06 +0100 Subject: [PATCH 3/7] linting --- impresso/resources/tools.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/impresso/resources/tools.py b/impresso/resources/tools.py index 4315556..a652903 100644 --- a/impresso/resources/tools.py +++ b/impresso/resources/tools.py @@ -182,9 +182,9 @@ def nel(self, text: str) -> NerContainer: ) def embed_image( - self, - image: bytes | Base64Str | str, - target: ImpressoImageEmbeddingRequestSearchTargetLiteral, + self, + image: bytes | Base64Str | str, + target: ImpressoImageEmbeddingRequestSearchTargetLiteral, ) -> Embedding: """Embed an image into a vector space. @@ -230,9 +230,9 @@ def embed_image( raise ValueError("Unexpected response format") def embed_text( - self, - text: str, - target: ImpressoTextEmbeddingRequestSearchTargetLiteral, + self, + text: str, + target: ImpressoTextEmbeddingRequestSearchTargetLiteral, ) -> Embedding: """Embed text into a vector space. From 8fa6dae35c1ecf848d1cc9005b6e7b27d8e22809 Mon Sep 17 00:00:00 2001 From: Emanuela Boros Date: Wed, 29 Oct 2025 10:51:08 +0100 Subject: [PATCH 4/7] linting --- impresso/resources/tools.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/impresso/resources/tools.py b/impresso/resources/tools.py index a652903..814ea91 100644 --- a/impresso/resources/tools.py +++ b/impresso/resources/tools.py @@ -189,8 +189,10 @@ def embed_image( """Embed an image into a vector space. Args: - image (bytes | Base64Str | str): Image to embed. Can be raw bytes, a base64-encoded string, a URL of an image or a path of a file. - target (ImpressoImageEmbeddingRequestSearchTargetLiteral): Target collection to embed the image into. Currently, only "image" is supported. + image (bytes | Base64Str | str): Image to embed. Can be raw bytes, a base64-encoded string, + a URL of an image or a path of a file. + target (ImpressoImageEmbeddingRequestSearchTargetLiteral): Target collection to embed the image into. + Currently, only "image" is supported. Returns: Embedding: The text embedding as a base64 string prefixed with model tag. From 562e35026ec522e403fef49109bf91a174fffbed Mon Sep 17 00:00:00 2001 From: Emanuela Boros Date: Wed, 29 Oct 2025 10:53:06 +0100 Subject: [PATCH 5/7] shortened output --- examples/notebooks/experiments.ipynb | 813 +-------------------------- 1 file changed, 28 insertions(+), 785 deletions(-) diff --git a/examples/notebooks/experiments.ipynb b/examples/notebooks/experiments.ipynb index 01a19d3..ebe5289 100644 --- a/examples/notebooks/experiments.ipynb +++ b/examples/notebooks/experiments.ipynb @@ -129,7 +129,7 @@ "" ], "text/plain": [ - "" + "" ] }, "execution_count": 2, @@ -223,799 +223,42 @@ }, { "cell_type": "code", - "execution_count": 5, - "id": "73fafa3f-9b12-491c-9f8a-c56736c48bd6", - "metadata": { - "scrolled": true - }, + "execution_count": 26, + "id": "c3dcd90c-0db4-4980-acb5-6f90c2ba7b77", + "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "{'id': 'indeplux-1912-06-14-a-i0001-s-27',\n", - " 'type_s': 's',\n", - " 'content_txt_fr': 'Mais c’ est une question qui ne peut se régler en congrès internationaux et c’ est pourquoi le pays cjui ne présente pas une natalité suffisante sera étranglé, ce qui ne sera d’ ailleurs qu’ une avance sur son sui- cide.',\n", - " 'ci_id_s': 'indeplux-1912-06-14-a-i0001',\n", - " 'gte_multi_v768': [-0.081427164,\n", - " 0.064372316,\n", - " -0.045108054,\n", - " 0.08742539,\n", - " -0.016204905,\n", - " -0.0032661548,\n", - " -0.08083391,\n", - " -0.030488549,\n", - " 0.01922982,\n", - " -0.066497795,\n", - " 0.04242271,\n", - " -0.036173802,\n", - " -0.0028986486,\n", - " 0.034270063,\n", - " -0.03690813,\n", - " 0.09999781,\n", - " 0.025211757,\n", - " -0.004169398,\n", - " 0.04152064,\n", - " 0.032867514,\n", - " 0.11520032,\n", - " 0.09198125,\n", - " 0.005486816,\n", - " 0.015264476,\n", - " 0.017409217,\n", - " -0.005969191,\n", - " 0.10060896,\n", - " -0.066738024,\n", - " -0.051272426,\n", - " 0.038004458,\n", - " -0.10215557,\n", - " -0.016743958,\n", - " 0.017888524,\n", - " -0.00096381706,\n", - " 0.052417602,\n", - " -0.073400766,\n", - " 0.047756754,\n", - " -0.018304978,\n", - " -0.03343914,\n", - " 0.015744846,\n", - " -0.035610653,\n", - " 0.01637089,\n", - " -0.051607937,\n", - " 0.0026041695,\n", - " -0.012169081,\n", - " 0.037903298,\n", - " -0.06327127,\n", - " -0.043894477,\n", - " -0.05351843,\n", - " 0.044884857,\n", - " 0.06338861,\n", - " 0.022319878,\n", - " 0.011649567,\n", - " -0.0054243333,\n", - " 0.026314184,\n", - " 0.027909214,\n", - " -0.09507064,\n", - " 0.061315954,\n", - " 0.07815464,\n", - " -0.014403484,\n", - " 0.031844497,\n", - " -0.0021377155,\n", - " 0.0064931754,\n", - " -0.025778398,\n", - " -0.0113039855,\n", - " 0.013106857,\n", - " 0.027689118,\n", - " -0.011624109,\n", - " 0.081417605,\n", - " 0.044308018,\n", - " -0.0781789,\n", - " 0.033899177,\n", - " 0.0021870101,\n", - " -0.019256592,\n", - " -0.011104092,\n", - " 0.03836033,\n", - " -0.019176582,\n", - " -0.0010315784,\n", - " -0.0137142325,\n", - " 0.013355355,\n", - " -0.013917252,\n", - " -0.02555351,\n", - " -0.016202243,\n", - " 0.018706385,\n", - " -0.050871357,\n", - " -0.0070682834,\n", - " 0.060611002,\n", - " 0.042384453,\n", - " 0.016053265,\n", - " 0.08681886,\n", - " -0.010137089,\n", - " 0.05954166,\n", - " -0.06806551,\n", - " -0.0068755522,\n", - " 0.019395446,\n", - " 0.059344202,\n", - " -0.016546328,\n", - " 0.019943053,\n", - " 0.049762107,\n", - " 0.048172187,\n", - " 0.0039899475,\n", - " -0.035056632,\n", - " 0.030599825,\n", - " -0.04716478,\n", - " 0.051026646,\n", - " -0.02126569,\n", - " 0.0044269883,\n", - " 0.0019362805,\n", - " -0.032534923,\n", - " -0.04946502,\n", - " 0.009440294,\n", - " 0.035840407,\n", - " -0.09611488,\n", - " -0.053630944,\n", - " -0.04836141,\n", - " -0.0097440295,\n", - " 0.057466105,\n", - " -0.0057519134,\n", - " 0.022386527,\n", - " 0.03149422,\n", - " -0.02305837,\n", - " -0.08078451,\n", - " -0.016198197,\n", - " 0.0053822338,\n", - " -0.08808732,\n", - " -0.023794789,\n", - " -0.024558565,\n", - " -0.057138834,\n", - " 0.052244026,\n", - " -0.007293488,\n", - " 0.1049111,\n", - " -0.0022571476,\n", - " -0.036102846,\n", - " -0.07726404,\n", - " -0.018246813,\n", - " -0.033013213,\n", - " -0.02333869,\n", - " 0.02077296,\n", - " 0.021713099,\n", - " -0.005465568,\n", - " -0.049857978,\n", - " 0.04799644,\n", - " -0.078355074,\n", - " 0.0021522,\n", - " -0.018461157,\n", - " 0.048754416,\n", - " -0.015175688,\n", - " -0.05485527,\n", - " 0.07835993,\n", - " 0.014683075,\n", - " -0.02412262,\n", - " 0.019611157,\n", - " 0.036663566,\n", - " 0.016612547,\n", - " 0.020707905,\n", - " -0.02157017,\n", - " -0.036986988,\n", - " 0.026372425,\n", - " -0.026306372,\n", - " -0.034135945,\n", - " 0.060493767,\n", - " 0.062349096,\n", - " 0.07548558,\n", - " -0.036325864,\n", - " -0.02152598,\n", - " 0.028488595,\n", - " 0.030044494,\n", - " 0.01852276,\n", - " 0.07674158,\n", - " -0.022839885,\n", - " -0.016950281,\n", - " 0.013122193,\n", - " 0.008219237,\n", - " -0.021939674,\n", - " -0.022592088,\n", - " -0.038033124,\n", - " 0.010979446,\n", - " 0.041204028,\n", - " -0.059076462,\n", - " 0.0033598582,\n", - " 0.02089602,\n", - " -0.059369985,\n", - " 0.0047558607,\n", - " -0.07706344,\n", - " 0.06355889,\n", - " 0.023710249,\n", - " -0.0041700536,\n", - " -0.07260834,\n", - " -0.035566736,\n", - " 0.038878743,\n", - " -0.019827707,\n", - " -0.036263216,\n", - " -0.063814625,\n", - " 0.017230544,\n", - " -0.0013633954,\n", - " -0.03908598,\n", - " 0.01250506,\n", - " 0.014394701,\n", - " 0.0041739405,\n", - " 0.0839863,\n", - " 0.0008519452,\n", - " 0.0104959095,\n", - " -0.013036082,\n", - " 0.015746057,\n", - " -0.05459077,\n", - " -0.052719757,\n", - " 0.0042646425,\n", - " 0.02956065,\n", - " 0.016120858,\n", - " -0.004233317,\n", - " 0.019077541,\n", - " -0.008454137,\n", - " 0.01175525,\n", - " -0.020472161,\n", - " -0.017467216,\n", - " -0.011110074,\n", - " -0.046194915,\n", - " -0.021829005,\n", - " 0.0131904315,\n", - " -0.002183448,\n", - " -0.0181923,\n", - " -0.01671806,\n", - " -0.03275726,\n", - " -0.0055113467,\n", - " 0.007338492,\n", - " 0.020452762,\n", - " -0.014988394,\n", - " 0.022865575,\n", - " -0.023398457,\n", - " 0.0048595606,\n", - " -0.011326758,\n", - " -0.0036041506,\n", - " 0.07581927,\n", - " 0.01818148,\n", - " -0.0033784837,\n", - " 0.021420475,\n", - " 0.039218593,\n", - " -0.02480191,\n", - " -0.021848006,\n", - " 0.041838992,\n", - " 0.011506943,\n", - " -0.012104254,\n", - " 0.001537347,\n", - " 0.03289704,\n", - " -0.061239846,\n", - " 0.038928296,\n", - " -0.012385192,\n", - " -0.032024134,\n", - " -0.013293794,\n", - " 0.015824921,\n", - " -0.009817402,\n", - " 0.031834833,\n", - " -0.0042468007,\n", - " 0.04379205,\n", - " -0.010797119,\n", - " -0.037814178,\n", - " -0.018777076,\n", - " 0.022162588,\n", - " 0.050620783,\n", - " -0.014713437,\n", - " -0.056102164,\n", - " -0.040111884,\n", - " -0.016369846,\n", - " -0.048014887,\n", - " 0.011927905,\n", - " -0.08738478,\n", - " 0.049479567,\n", - " 0.002872294,\n", - " 0.018098652,\n", - " -0.026732583,\n", - " -0.019144585,\n", - " 0.013347716,\n", - " -0.012236467,\n", - " 0.039242662,\n", - " 0.020409267,\n", - " 0.026534997,\n", - " 0.021626161,\n", - " -0.049137626,\n", - " 0.057768505,\n", - " 0.024537649,\n", - " 0.040146396,\n", - " -0.030630916,\n", - " -0.012266775,\n", - " 0.008592031,\n", - " -0.06309963,\n", - " 0.058924045,\n", - " 0.027965445,\n", - " -0.0066002603,\n", - " -0.060511287,\n", - " 0.02022797,\n", - " 0.022165498,\n", - " -0.043309417,\n", - " -0.00970387,\n", - " 0.03280196,\n", - " 0.05165125,\n", - " -0.027301418,\n", - " -0.024620913,\n", - " 0.034908008,\n", - " 0.030793473,\n", - " 0.0042416714,\n", - " -0.016695043,\n", - " -0.016573505,\n", - " 0.0034687242,\n", - " 0.009735219,\n", - " -0.04334127,\n", - " -0.0051383646,\n", - " -0.0029800101,\n", - " -0.03669362,\n", - " -0.013573973,\n", - " 0.02915002,\n", - " 0.053568836,\n", - " 0.013559603,\n", - " -0.0056021395,\n", - " -0.083493836,\n", - " 0.048657723,\n", - " -0.024513677,\n", - " 0.011142334,\n", - " 0.024816891,\n", - " -0.016300842,\n", - " -0.033580966,\n", - " 0.02569195,\n", - " 0.009701036,\n", - " -0.051402524,\n", - " 0.04622702,\n", - " -0.028156225,\n", - " -0.022232272,\n", - " -0.015802791,\n", - " 0.0014903932,\n", - " -0.040654257,\n", - " 0.0014043513,\n", - " 0.034458928,\n", - " 0.034616753,\n", - " 0.022009227,\n", - " -0.053867683,\n", - " 0.025601747,\n", - " 0.08592088,\n", - " 0.031311963,\n", - " 0.0006002426,\n", - " 0.02619659,\n", - " 0.004906178,\n", - " -0.0008670905,\n", - " 0.037017092,\n", - " -0.06659331,\n", - " 0.054778777,\n", - " -0.018856762,\n", - " -0.013714602,\n", - " -0.0010605609,\n", - " 0.03824293,\n", - " 0.03665221,\n", - " 0.021349635,\n", - " -0.007914992,\n", - " 0.02346739,\n", - " 0.05344404,\n", - " -0.0035946732,\n", - " -0.007898519,\n", - " 0.003189902,\n", - " 0.017389607,\n", - " 0.059460696,\n", - " -0.018158963,\n", - " 0.06321497,\n", - " 0.057064842,\n", - " -0.045017887,\n", - " 0.00028358883,\n", - " 0.02802503,\n", - " 0.025817374,\n", - " -0.05629147,\n", - " -0.04575568,\n", - " 0.0026548724,\n", - " 0.05056999,\n", - " 0.019218508,\n", - " 0.0021371325,\n", - " 0.021273365,\n", - " 0.02881533,\n", - " 0.07721803,\n", - " -0.045122124,\n", - " 0.046677075,\n", - " -0.034335572,\n", - " 0.037475634,\n", - " 0.018491682,\n", - " 0.0051161293,\n", - " 0.019452339,\n", - " 0.028822228,\n", - " 0.109846845,\n", - " -0.013732984,\n", - " 0.014720311,\n", - " 0.0011648148,\n", - " -0.002483864,\n", - " -0.041083615,\n", - " -0.021729276,\n", - " -0.031135181,\n", - " -0.012765439,\n", - " -0.034220085,\n", - " -0.025189184,\n", - " 0.017646268,\n", - " 0.023410823,\n", - " 0.012667995,\n", - " 0.053882256,\n", - " 0.050381634,\n", - " -0.04154851,\n", - " -0.025424054,\n", - " 0.056466915,\n", - " 0.014838826,\n", - " 0.004047925,\n", - " -0.010193228,\n", - " 0.030313522,\n", - " -0.012074564,\n", - " 0.01720908,\n", - " 0.01081676,\n", - " 0.042463094,\n", - " 0.029379077,\n", - " 0.051904935,\n", - " -0.0089294,\n", - " 0.0012408567,\n", - " -0.03142283,\n", - " -0.0015596739,\n", - " 0.03380737,\n", - " 0.019032702,\n", - " 0.021951968,\n", - " 0.11533221,\n", - " -0.007856628,\n", - " 0.02281904,\n", - " 0.00881275,\n", - " 0.020597987,\n", - " -0.02549735,\n", - " -0.030028533,\n", - " -0.06013915,\n", - " 0.0031522315,\n", - " 0.017439466,\n", - " 0.04207593,\n", - " 0.091469854,\n", - " -0.015765613,\n", - " 0.0149031235,\n", - " -0.01956561,\n", - " -0.002414244,\n", - " -0.1094421,\n", - " 0.005633813,\n", - " -0.0033078243,\n", - " -0.046207964,\n", - " 0.0033252954,\n", - " 0.01700336,\n", - " -0.064000346,\n", - " 0.013695957,\n", - " 0.018813917,\n", - " -0.019596778,\n", - " -0.018768733,\n", - " -0.062085226,\n", - " -0.04393183,\n", - " 0.01740412,\n", - " 0.0068095806,\n", - " 0.02982634,\n", - " -0.031117061,\n", - " 0.0010879937,\n", - " -0.030221133,\n", - " -0.02305694,\n", - " 0.012205767,\n", - " 0.020197889,\n", - " -0.011025782,\n", - " -0.011664094,\n", - " -0.0087072505,\n", - " -0.030868791,\n", - " -0.0022526246,\n", - " 0.009358584,\n", - " -0.036634415,\n", - " 0.026896648,\n", - " 0.05941364,\n", - " 0.019537749,\n", - " -0.01794697,\n", - " 0.038881943,\n", - " 0.06502216,\n", - " 0.022962114,\n", - " 0.03018654,\n", - " 0.026737124,\n", - " 0.019744167,\n", - " -0.026662428,\n", - " 0.012199454,\n", - " -0.008034174,\n", - " 0.0067995223,\n", - " 0.023114827,\n", - " 0.017662069,\n", - " -0.0037633989,\n", - " -0.020161726,\n", - " 0.01888501,\n", - " -0.032249585,\n", - " -0.030862305,\n", - " -0.03098063,\n", - " 0.014843968,\n", - " 0.022338323,\n", - " -0.08554132,\n", - " 0.032697104,\n", - " 0.0766141,\n", - " 0.06331765,\n", - " 0.0063295616,\n", - " -0.046704944,\n", - " -0.015937336,\n", - " 0.0146816345,\n", - " 0.024641693,\n", - " 0.022917889,\n", - " -0.047505036,\n", - " 0.0017036259,\n", - " 0.05883194,\n", - " -0.013983027,\n", - " -0.007955594,\n", - " -0.059356853,\n", - " 0.010960551,\n", - " 0.03761545,\n", - " 0.004573043,\n", - " 0.053301178,\n", - " -0.030775413,\n", - " 0.013350438,\n", - " 0.02404047,\n", - " -0.069119535,\n", - " 0.027269974,\n", - " 0.0013833656,\n", - " -0.058948528,\n", - " 0.016748793,\n", - " -0.022794815,\n", - " -0.024996081,\n", - " 0.03278682,\n", - " -0.015970118,\n", - " 0.0064338837,\n", - " 0.025020966,\n", - " -0.025259184,\n", - " -0.07177622,\n", - " 0.019871945,\n", - " -0.05269971,\n", - " 0.017440531,\n", - " 0.0117028095,\n", - " -0.006656424,\n", - " -0.010291318,\n", - " -0.017315334,\n", - " -0.007990969,\n", - " 0.086795285,\n", - " 0.020211952,\n", - " 0.009114601,\n", - " 0.059573226,\n", - " 0.040704682,\n", - " 0.025457015,\n", - " -0.031309012,\n", - " 0.0058753267,\n", - " 0.04901623,\n", - " -0.0122652855,\n", - " -0.018044721,\n", - " -0.007143741,\n", - " 0.002831681,\n", - " -0.012250971,\n", - " -0.026678441,\n", - " 0.032056082,\n", - " -0.030600509,\n", - " -0.04300202,\n", - " -0.031419076,\n", - " 0.04335907,\n", - " 0.05062743,\n", - " 0.06994422,\n", - " -0.0031660371,\n", - " -0.070930205,\n", - " -0.03823314,\n", - " 0.0006152355,\n", - " 0.009303026,\n", - " -0.008590888,\n", - " -0.01509825,\n", - " -0.022812745,\n", - " -0.08762697,\n", - " 0.051922265,\n", - " 0.04894216,\n", - " 0.0057275896,\n", - " -0.0015417227,\n", - " -0.013337219,\n", - " -0.04094926,\n", - " 0.02615881,\n", - " 0.015957305,\n", - " -0.008662798,\n", - " 0.022658108,\n", - " -0.004368052,\n", - " -0.06387781,\n", - " -0.00049686554,\n", - " -0.010450126,\n", - " -0.010210296,\n", - " 0.031181276,\n", - " -0.027020259,\n", - " 0.021817883,\n", - " -0.020034732,\n", - " 0.06912386,\n", - " -0.009485199,\n", - " -0.017461605,\n", - " -0.036170892,\n", - " 0.015329548,\n", - " 0.0062945304,\n", - " 0.045467105,\n", - " -0.044223413,\n", - " -0.004715235,\n", - " -0.033207588,\n", - " -0.0058536036,\n", - " 0.0050861333,\n", - " -0.06395814,\n", - " -0.004318634,\n", - " 0.024803467,\n", - " 0.008540717,\n", - " 0.02915922,\n", - " 0.059703548,\n", - " 0.02672467,\n", - " 0.013200832,\n", - " -0.027720576,\n", - " 0.00977768,\n", - " -0.038109757,\n", - " -0.03530302,\n", - " 0.033653025,\n", - " 0.026344186,\n", - " -0.07872108,\n", - " -0.03482698,\n", - " -0.029127572,\n", - " -0.0055903303,\n", - " -0.007942379,\n", - " 0.002264677,\n", - " 0.03818393,\n", - " -0.04583064,\n", - " 0.018037342,\n", - " -0.085961446,\n", - " -0.039332535,\n", - " -9.797573e-05,\n", - " 0.022565985,\n", - " -0.02423783,\n", - " 0.0027169255,\n", - " 0.041872244,\n", - " -0.03147955,\n", - " 0.02825741,\n", - " -0.008287027,\n", - " -0.04118363,\n", - " 0.029515438,\n", - " -0.039799336,\n", - " -0.0266588,\n", - " 0.02826509,\n", - " -0.02063068,\n", - " -0.006316049,\n", - " 0.017246423,\n", - " 0.034976125,\n", - " 0.0076519162,\n", - " -0.030508237,\n", - " 0.0037944815,\n", - " 0.027766814,\n", - " -0.08801824,\n", - " 0.008386495,\n", - " 0.010155254,\n", - " 0.047535814,\n", - " 0.0467276,\n", - " -0.012654169,\n", - " -0.023404893,\n", - " 0.009156073,\n", - " -0.021613082,\n", - " -0.022608759,\n", - " 0.0040091854,\n", - " 0.027937712,\n", - " 0.0017836906,\n", - " -0.029016731,\n", - " -0.014328147,\n", - " -0.013694352,\n", - " 0.01624316,\n", - " -0.087653704,\n", - " -0.007499973,\n", - " 0.0014776542,\n", - " 0.023297846,\n", - " 0.017909396,\n", - " 0.026473945,\n", - " 0.049817335,\n", - " -0.004742915,\n", - " -0.045145947,\n", - " -0.005817356,\n", - " 0.0093169315,\n", - " -0.0024441234,\n", - " -0.020449957,\n", - " -0.057113476,\n", - " -0.00037673535,\n", - " -0.0068436866,\n", - " 0.049108807,\n", - " -0.004650932,\n", - " -0.03991428,\n", - " 0.041935865,\n", - " -0.0046782154,\n", - " -0.006373373,\n", - " -0.02583609,\n", - " 0.010704986,\n", - " 0.020917885,\n", - " -0.03886426,\n", - " -0.022924274,\n", - " 0.026235584,\n", - " -0.016595159,\n", - " 0.0064262864,\n", - " -0.006728229,\n", - " 0.04023094,\n", - " 0.018823523,\n", - " -0.021455951,\n", - " -0.034144104,\n", - " 0.007861527,\n", - " -0.00029349345,\n", - " -0.008764708,\n", - " 0.02014379,\n", - " -0.0150536,\n", - " 0.04630012,\n", - " 0.046140317,\n", - " 0.020522414,\n", - " 0.012370299,\n", - " 0.026588684,\n", - " 0.0010963973,\n", - " 0.047540367,\n", - " -0.030359069,\n", - " -0.013518566,\n", - " -0.022742666,\n", - " -0.0046805856,\n", - " 0.014406342,\n", - " -0.007278617,\n", - " -0.012485435,\n", - " 0.04940796,\n", - " -0.04546034,\n", - " -0.020017812,\n", - " 0.02772044,\n", - " -0.005244903,\n", - " -0.03883373,\n", - " -0.0093254745,\n", - " 0.02377589,\n", - " -0.058478873,\n", - " 0.026416734,\n", - " 0.020168163,\n", - " -0.010474008,\n", - " -0.012232645,\n", - " -0.0027875488,\n", - " 0.0048259352,\n", - " -0.03345372,\n", - " 0.023432989,\n", - " 0.0073413025,\n", - " -0.004630064,\n", - " -0.016431082,\n", - " -0.010867781,\n", - " 0.046610504,\n", - " 0.02221005,\n", - " -0.035439335,\n", - " 0.021267762,\n", - " 0.003914809,\n", - " 0.0372266,\n", - " -0.05508867,\n", - " 0.0026225722,\n", - " -0.020968309,\n", - " 0.0037491478,\n", - " -0.015431687,\n", - " 0.069426954,\n", - " 0.006881036,\n", - " -0.0059120427,\n", - " 0.023701912,\n", - " -0.023184957,\n", - " 0.018712236,\n", - " 0.006075447,\n", - " 0.032562926,\n", - " -0.023184566,\n", - " 0.014065631,\n", - " 0.0150226895,\n", - " -0.002041589,\n", - " -0.0266023,\n", - " -0.0013457921,\n", - " 0.004231847,\n", - " -0.052936506,\n", - " -0.0733579,\n", - " 0.02305891,\n", - " 0.0118407635,\n", - " 0.026815364,\n", - " 0.03814409,\n", - " 0.008659009,\n", - " -0.017255636,\n", - " 0.02480575,\n", - " -0.0037373884,\n", - " 0.039746176],\n", - " 'lg_s': 'fr',\n", - " '_version_': 1843522628974804992,\n", - " '_root_': 'indeplux-1912-06-14-a-i0001-s-27'}" + "['id',\n", + " 'imp_ids_ss',\n", + " 'surfaces_ss',\n", + " 'ci_ids_ss',\n", + " 'mention_keys_ss',\n", + " 'ci_lg_s',\n", + " 'wiki_masterlabel_s',\n", + " 'wiki_url_s',\n", + " 'date_of_birth_dt',\n", + " 'date_of_death_dt',\n", + " 'wkd_occupations_ss',\n", + " 'wkd_occupation_qids_ss',\n", + " 'wkd_entity_types_ss',\n", + " 'wiki_summaries_t',\n", + " 'contexts_ss',\n", + " 'entity_mixed_emb_v768',\n", + " 'entity_encyc_emb_v768',\n", + " 'entity_media_emb_v768',\n", + " '_version_',\n", + " '_root_']" ] }, - "execution_count": 5, + "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "docs[0]" + "list(docs[0].keys())" ] }, { @@ -1118,7 +361,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 10, "id": "09ec22e2-8605-47fe-ae74-10371ffb8453", "metadata": {}, "outputs": [], @@ -1570,7 +813,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 24, "id": "677ca42e", "metadata": {}, "outputs": [ From a7e3690607a1dcbc046e247f0a6565cbfacc42a4 Mon Sep 17 00:00:00 2001 From: Roman Kalyakin Date: Wed, 29 Oct 2025 10:55:49 +0100 Subject: [PATCH 6/7] formatting --- impresso/resources/tools.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/impresso/resources/tools.py b/impresso/resources/tools.py index 814ea91..b73cc11 100644 --- a/impresso/resources/tools.py +++ b/impresso/resources/tools.py @@ -182,9 +182,9 @@ def nel(self, text: str) -> NerContainer: ) def embed_image( - self, - image: bytes | Base64Str | str, - target: ImpressoImageEmbeddingRequestSearchTargetLiteral, + self, + image: bytes | Base64Str | str, + target: ImpressoImageEmbeddingRequestSearchTargetLiteral, ) -> Embedding: """Embed an image into a vector space. @@ -232,9 +232,9 @@ def embed_image( raise ValueError("Unexpected response format") def embed_text( - self, - text: str, - target: ImpressoTextEmbeddingRequestSearchTargetLiteral, + self, + text: str, + target: ImpressoTextEmbeddingRequestSearchTargetLiteral, ) -> Embedding: """Embed text into a vector space. From afcdcae15458bb11ca8fb5d5756760f23c981144 Mon Sep 17 00:00:00 2001 From: Roman Kalyakin Date: Wed, 29 Oct 2025 10:57:43 +0100 Subject: [PATCH 7/7] formatted docstring --- impresso/resources/tools.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/impresso/resources/tools.py b/impresso/resources/tools.py index b73cc11..cc09715 100644 --- a/impresso/resources/tools.py +++ b/impresso/resources/tools.py @@ -190,12 +190,12 @@ def embed_image( Args: image (bytes | Base64Str | str): Image to embed. Can be raw bytes, a base64-encoded string, - a URL of an image or a path of a file. + a URL of an image, or a path to a file. target (ImpressoImageEmbeddingRequestSearchTargetLiteral): Target collection to embed the image into. - Currently, only "image" is supported. + Currently, only "image" is supported. Returns: - Embedding: The text embedding as a base64 string prefixed with model tag. + Embedding: The image embedding as a base64 string prefixed with model tag. """ image_as_base64: str if isinstance(image, bytes):