first commit

Author: vasilescur

README.md

@@ -0,0 +1,67 @@
+# `parse_context`
+
+This program uses the OpenAI API, powered by GPT-3, to power the logic of a context-based
+active-listening voice assistant. The context of this software is:
+
+- Humans have a conversation, which is recorded and transcribed in real time.
+- (**THIS PROGRAM**) The conversation is sent to the OpenAI API along with a few-shot list of examples. The API returns a 
+detected context, suggestions for what outputs would be useful to the humans, and a list of data sources 
+for achieving those outputs.
+- The voice assistant presents the data to the user to augment the conversation.
+
+## Requirements
+
+- Python 3
+- OpenAI Python Client
+
+### Installation
+
+Install Python. Install Pip for Python3. Then run:
+
+```bash
+pip3 install -r ./requirements.txt
+```
+
+To update the requirements file after changing, you can use:
+
+```bash
+pip3 freeze > ./requirements.txt
+```
+
+Or
+
+```bash
+pip3 freeze | grep openai > ./requirements.txt
+```
+
+## Usage
+
+### Interactive Mode
+
+To use interactive mode, make sure the `INTERACTIVE` flag at the top of `parse_context.py` is set to `True`.
+
+Then, run `python3 parse_context.py`. You can enter the conversation on the command line
+in the following format, using `/end` to stop.
+
+```
+A: Hey, what tech stack do you think we should use for the new app?
+B: What app?
+A: The dating app we are developing. It needs to be cross-platform mobile.
+B: Oh, okay. Um... I don't really know any good frameworks
+/end
+```
+
+The result will be printed to `STDOUT` (default is the terminal window).
+
+### Non-interactive mode
+
+To use non-interactive mode, make sure the `INTERACTIVE` flag at the top of `parse_context.py` is set to `False`.
+
+Then, run the program while passing your conversation to standard input (`STDIN`). For example, if the above
+conversation were placed in a file located at `./conversations/tech_stack.txt`, we could run:
+
+```bash
+cat ./conversations/tech_stack.txt | python3 parse_context.py
+```
+
+And the result will be printed to `STDOUT`.

conversations/actor.txt

@@ -0,0 +1,4 @@
+A: I watched Terminator last night.
+B: Oh, cool! I love that movie, it's a classic.
+A: Arnold Schwarzenegger was so good.
+B: Yeah, I agree.

conversations/cooking.txt

@@ -0,0 +1,4 @@
+A: Hey, what do you think we should cook for dinner tonight?
+B: Dunno. Let's check the fridge.
+A: Okay. Looks like we've got chicken, beef, lettuce, rice, mustard, mayo, taco shells, and corn.
+B: How about tacos?

conversations/dinner.txt

@@ -0,0 +1,2 @@
+A: Hey Mike, let's get dinner tonight.
+B: Okay, sure! What restaurants do you know in the area?

conversations/tech_stack.txt

@@ -0,0 +1,4 @@
+A: Hey, what tech stack do you think we should use for the new app?
+B: What app?
+A: The dating app we are developing. It needs to be cross-platform mobile.
+B: Oh, okay. Um... I don't really know any good frameworks

parse_context.py

@@ -0,0 +1,60 @@
+"""
+Author: Radu Vasilescu
+Date:   2020-11-10
+"""
+
+import os
+import sys
+import openai
+
+"""
+Determines the input method for the script. 
+
+A value of True reads the program's input from the command line interactively.
+A value of False reads the program's input from the process' STDIN. An example of 
+non-interactive usage is:
+
+    cat ./conversations/dinner.txt | python3 parse_content.py
+"""
+INTERACTIVE : bool = False
+
+openai.api_key : str = os.environ["OPENAI_API_KEY"]
+
+# Set up 4-shot example prompts:
+examples : str = "The following is a list of conversations between humans. A voice-activated AI suggests information that might be relevant in the context of the conversation.\n\nA: I'm going to leave for work soon.\nB: Okay, I'm leaving too.\nA: Let me get dressed first.\nContext: Two people are about to leave for work.\nUseful Output: Current weather, current traffic, estimated commute time, reminders\nRelevant Data Sources: Query Google Weather API to get current weather, query Google Maps API to get traffic and commute time, query Reminders app to get reminders.\n\nA: Have you seen that movie, Avengers Endgame?\nB: Oh, yeah! I saw it when it came out. I loved Iron Man in that series!\nA: Who played him again? \nB: I don't remember.\nContext: Two people are wondering who played Iron Man in the film Avengers Endgame\nUseful Output: Tony Stark\nRelevant Data Sources: Query Google Search for \"Who plays Iron Man in Avengers Endgame?\"\n\nA: So, when do you guys want to meet up later?\nB: I don't know, I have a pretty busy evening\nC: I'm free after 5:00pm\nA: Let me look at my schedule.\nContext: A group of people is trying to schedule an event this evening.\nUseful Output: Today's remaining calendar events.\nRelevant Data Sources: Query Google Calendar API for events after 5pm today.\n\nA: I have to pick my daughter up from school today.\nB: Okay, what time is that going to be?\nContext: Two people are talking about a plan to pick someone up from school\nUseful Output: Reminder to pick up the child, current traffic conditions to the school, estimated time to the school\nRelevant Data Sources: Add a reminder to the Reminders app, query Google Maps API for current traffic and school location, query Google Maps API for estimated travel time\n\n"
+
+start_sequence : str = "Context:"
+
+conversation : str = ""
+if INTERACTIVE:
+    # Read the conversation from the console
+    print('Enter conversation. Use /end to signal the end.\n')
+
+    while (line := input()) != '/end':
+        conversation += line + "\n"
+else:
+    # Read the conversation from standard input
+    for line in sys.stdin:
+        if line == "\n" or line == "/end":
+            print("Do not include neither newlines nor /end in the input (INTERACTIVE = %s)", str(INTERACTIVE))
+            exit(1)
+        conversation += line
+
+print('Generating completion...')
+
+response = openai.Completion.create(
+  engine = "davinci",
+  prompt = examples + conversation + start_sequence,
+  temperature = 0.7,
+  max_tokens = 64,
+  top_p = 1,
+  stop = ["\n\n"]
+)
+
+response_text : str = response["choices"][0]["text"]
+response_split = response_text.split("\n")
+gen_context, gen_output, gen_sources = response_split[0].strip(), response_split[1].strip(), response_split[2].strip()
+
+print('Context: ' + gen_context)
+print(gen_output)
+print(gen_sources)

requirements.txt

@@ -0,0 +1 @@
+openai==0.2.6