使用azure openai出现调用失败的现象 #75
Description
请问您的项目支持azure openai服务吗或者deepseek、zhipu AI的embedding 模型吗？或者是我config.yaml调用格式有问题？麻烦您解答一下。
以下是我的config.yaml，用的是azure openai的服务：
但是出现多次调用OpenAILLM.acompletion_text时返回Error code: 404 - Resource not found，重试后仍失败的现象，terminal具体输出结果：(graphrag) vsc@a100-4:/opt/GraphRAG$ python main.py -opt Option/Config2.yaml -dataset_name cs
####################################################################################################
| __ _ / | | / |/ __ | \ | |
| | | || || | __ | | | \ / | | | | | |
| | | || || | | | | | | |/| | | | | . ` |
| || || || || || || | | | || | |\ |
|/___|_____|| ||___/|| _|
╔════════════════════════════════════════════════════════════════════════════════════════════════════════╗
║ Welcome to DIGIMON: Deep Analysis of Graph-Based RAG Systems. ║
║ ║
║ Unlock advanced insights with our comprehensive tool for evaluating and optimizing RAG models. ║
║ ║
║ You can freely combine any graph-based RAG algorithms you desire. We hope this will be helpful to you! ║
╚════════════════════════════════════════════════════════════════════════════════════════════════════════╝
####################################################################################################
2025-04-27 10:58:58.199 | INFO | Core.Chunk.DocChunk:build_chunks:27 - Starting chunk the given documents
2025-04-27 10:58:58.716 | INFO | Core.Storage.ChunkKVStorage:_persist:105 - Writing data into opt/GraphRAG/result/cs/nbits_2/chunk_storage_chunk_data_idx.pkl and opt/GraphRAG/result/cs/nbits_2/chunk_storage_chunk_data_key.pkl
2025-04-27 10:58:58.750 | INFO | Core.Chunk.DocChunk:build_chunks:74 - ✅ Finished the chunking stage
2025-04-27 10:58:58.768 | INFO | Core.GraphRAG:_update_costs_info:205 - Chunking stage cost: Total prompt token: 0, Total completeion token: 0, Total cost: 0
2025-04-27 10:58:58.768 | INFO | Core.GraphRAG:_update_costs_info:207 - Chunking time(s): 0.57
2025-04-27 10:58:58.768 | INFO | Core.Graph.BaseGraph:build_graph:41 - Starting build graph for the given documents
2025-04-27 10:58:58.768 | INFO | Core.Storage.NetworkXStorage:load_nx_graph:27 - Attempting to load the graph from: opt/GraphRAG/result/cs/nbits_2/graph_storage_nx_data.graphml
2025-04-27 10:58:58.770 | INFO | Core.Storage.NetworkXStorage:load_nx_graph:31 - Successfully loaded graph from: opt/GraphRAG/result/cs/nbits_2/graph_storage_nx_data.graphml with 0 nodes and 0 edges
2025-04-27 10:58:58.770 | INFO | Core.Graph.BaseGraph:build_graph:50 - ✅ Finished the graph building stage
2025-04-27 10:58:58.770 | INFO | Core.GraphRAG:_update_costs_info:205 - Build Graph stage cost: Total prompt token: 0, Total completeion token: 0, Total cost: 0
2025-04-27 10:58:58.770 | INFO | Core.GraphRAG:_update_costs_info:207 - Build Graph time(s): 0.00
2025-04-27 10:58:58.770 | INFO | Core.Index.BaseIndex:build_index:13 - Starting insert elements of the given graph into vector database
2025-04-27 10:58:58.770 | INFO | Core.Index.BaseIndex:build_index:17 - Loading index from the file opt/GraphRAG/result/cs/nbits_2/entities_vdb
2025-04-27 10:58:58.773 | INFO | Core.Index.BaseIndex:build_index:29 - ✅ Finished starting insert entities of the given graph into vector database
2025-04-27 10:58:58.774 | INFO | Core.Graph.BaseGraph:augment_graph_by_similarity_search:176 - Starting augment the existing graph with similariy edges
0it [00:00, ?it/s]
2025-04-27 10:58:58.775 | INFO | Core.Graph.BaseGraph:augment_graph_by_similarity_search:223 - Augmenting graph with 0 edges
2025-04-27 10:58:58.775 | INFO | Core.Graph.BaseGraph:augment_graph_by_similarity_search:227 - ✅ Finished augment the existing graph with similariy edges
2025-04-27 10:58:58.776 | INFO | Core.GraphRAG:build_e2r_r2c_maps:193 - Starting build two maps: 1️⃣ entity <-> relationship; 2️⃣ relationship <-> chunks
2025-04-27 10:58:58.776 | INFO | Core.Storage.PickleBlobStorage:load:21 - Forcing rebuild the mapping for: opt/GraphRAG/result/cs/nbits_2/map_e2r_blob_data.pkl.
2025-04-27 10:58:58.776 | INFO | Core.Storage.PickleBlobStorage:persist:50 - Saving blob storage 'opt/GraphRAG/result/cs/nbits_2/map_e2r_blob_data.pkl'.
2025-04-27 10:58:58.776 | INFO | Core.Storage.PickleBlobStorage:load:21 - Forcing rebuild the mapping for: opt/GraphRAG/result/cs/nbits_2/map_r2c_blob_data.pkl.
1868
1868
2025-04-27 10:58:58.777 | INFO | Core.Storage.PickleBlobStorage:persist:50 - Saving blob storage 'opt/GraphRAG/result/cs/nbits_2/map_r2c_blob_data.pkl'.
2025-04-27 10:58:58.777 | INFO | Core.GraphRAG:build_e2r_r2c_maps:200 - ✅ Finished building the two maps
2025-04-27 10:58:58.777 | INFO | Core.Index.BaseIndex:build_index:13 - Starting insert elements of the given graph into vector database
2025-04-27 10:58:58.777 | INFO | Core.Index.BaseIndex:build_index:17 - Loading index from the file opt/GraphRAG/result/cs/nbits_2/relations_vdb
2025-04-27 10:58:58.778 | INFO | Core.Index.BaseIndex:build_index:29 - ✅ Finished starting insert entities of the given graph into vector database
2025-04-27 10:58:58.779 | INFO | Core.GraphRAG:_update_costs_info:205 - Index Building stage cost: Total prompt token: 0, Total completeion token: 0, Total cost: 0
2025-04-27 10:58:58.779 | INFO | Core.GraphRAG:_update_costs_info:207 - Index Building time(s): 0.01
2025-04-27 10:58:58.779 | INFO | Core.GraphRAG:_build_retriever_context:176 - Building retriever context for the current execution
2025-04-27 10:58:59.731 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 0.951(s), this was the 1st time calling it.
2025-04-27 10:59:00.787 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 2.007(s), this was the 2nd time calling it.
2025-04-27 10:59:03.044 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 4.264(s), this was the 3rd time calling it.
2025-04-27 10:59:03.996 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 5.216(s), this was the 4th time calling it.
2025-04-27 10:59:11.512 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 12.732(s), this was the 5th time calling it.
2025-04-27 10:59:20.641 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 21.861(s), this was the 6th time calling it.
2025-04-27 10:59:20.642 | ERROR | Core.Common.Utils:log_and_reraise:286 - Retry attempts exhausted. Last exception: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2025-04-27 10:59:20.642 | WARNING | Core.Common.Utils:log_and_reraise:287 -
Recommend going to https://deepwisdom.feishu.cn/wiki/MsGnwQBjiif9c3koSJNcYaoSnu4#part-XdatdVlhEojeAfxaaEZcMV3ZniQ
See FAQ 5.8
2025-04-27 10:59:20.642 | ERROR | Core.Query.BaseQuery:extract_query_entities:55 - Error in Retrieval NER: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
/opt/GraphRAG/Core/Common/Utils.py:267: RuntimeWarning: invalid value encountered in divide
return (x - np.min(x)) / (np.max(x) - np.min(x))
2025-04-27 10:59:20.644 | INFO | Core.Query.PPRQuery:_retrieve_relevant_contexts:56 - Entering the ir-cot iteration: 2
2025-04-27 10:59:20.890 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 0.245(s), this was the 1st time calling it.
2025-04-27 10:59:21.373 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 0.728(s), this was the 2nd time calling it.
2025-04-27 10:59:22.348 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 1.703(s), this was the 3rd time calling it.
2025-04-27 10:59:23.071 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 2.426(s), this was the 4th time calling it.
2025-04-27 10:59:29.082 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 8.437(s), this was the 5th time calling it.
2025-04-27 10:59:38.578 | WARNING | tenacity.after:log_it:44 - Finished call to 'Core.Provider.OpenaiApi.OpenAILLM.acompletion_text' after 17.933(s), this was the 6th time calling it.
2025-04-27 10:59:38.578 | ERROR | Core.Common.Utils:log_and_reraise:286 - Retry attempts exhausted. Last exception: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
2025-04-27 10:59:38.579 | WARNING | Core.Common.Utils:log_and_reraise:287 -
Recommend going to https://deepwisdom.feishu.cn/wiki/MsGnwQBjiif9c3koSJNcYaoSnu4#part-XdatdVlhEojeAfxaaEZcMV3ZniQ
See FAQ 5.8
Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}
Traceback (most recent call last):
File "/opt/GraphRAG/main.py", line 79, in
save_path = wrapper_query(query_dataset, digimon, result_dir)
File "/opt/GraphRAG/main.py", line 39, in wrapper_query
res = asyncio.run(digimon.query(query["question"]))
File "/home/vsc/miniconda3/envs/graphrag/lib/python3.10/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/home/vsc/miniconda3/envs/graphrag/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/opt/GraphRAG/Core/GraphRAG.py", line 290, in query
response = await self._querier.query(query)
File "/opt/GraphRAG/Core/Query/BaseQuery.py", line 22, in query
context = await self._retrieve_relevant_contexts(query=query)
File "/opt/GraphRAG/Core/Query/PPRQuery.py", line 67, in _retrieve_relevant_contexts
new_passages, new_scores = await self._retriever.retrieve_relevant_content(query=query,
File "/opt/GraphRAG/Core/Retriever/MixRetriever.py", line 19, in retrieve_relevant_content
return await self.retrievers[type].retrieve_relevant_content(mode=mode, **kwargs)
File "/opt/GraphRAG/Core/Retriever/BaseRetriever.py", line 25, in retrieve_relevant_content
return await retrieve_fun(self, **kwargs)
File "/opt/GraphRAG/Core/Retriever/ChunkRetriever.py", line 115, in _find_relevant_chunks_by_ppr
seed_entities = await self.link_query_entities(seed_entities)
File "/opt/GraphRAG/Core/Retriever/BaseRetriever.py", line 96, in link_query_entities
entities.append(node_datas[0])
IndexError: list index out of range