KeyError in _find_most_related_community_from_entities

[RoadToNowhereX]

After extraction and indexing, I would get those KeyErrors whatever I ask the LLM.

Frontend: kotaemon
Python 3.10
Local LLM: Nemo_saiga
Local Embedding Model: gte-qwen2-7B

INFO:httpx:HTTP Request: POST http://127.0.0.1:1234/v1/chat/completions "HTTP/1.1 200 OK"
User-id: 1, can see public conversations: True
Session reasoning type None use mindmap (default) use citation (default) language (default)
Session LLM
Reasoning class <class 'ktem.reasoning.simple.FullDecomposeQAPipeline'>
Reasoning state {'app': {'regen': False}, 'pipeline': {}}
Thinking ...
Chosen rewrite pipeline DecomposeQuestionPipeline(
(llm): ChatOpenAI(api_key=null, base_url=http://127.0.0...., frequency_penalty=None, logit_bias=None, logprobs=None, max_retries=None, max_retries_=2, max_tokens=4096, model=gguf/embedding-..., n=1, organization=None, presence_penalty=None, stop=None, temperature=None, timeout=None, tool_choice=None, tools=None, top_logprobs=None, top_p=None)
)
INFO:httpx:HTTP Request: POST http://127.0.0.1:1234/v1/chat/completions "HTTP/1.1 200 OK"
Rewrite result []
searching in doc_ids []
INFO:ktem.index.file.pipelines:Skip retrieval because of no selected files: DocumentRetrievalPipeline(
(vector_retrieval): <function Function.prepare_child..exec at 0x0000024B5BFF4160>
(embedding): <function Function.prepare_child..exec at 0x0000024B5BFF4670>
)
searching in doc_ids []
INFO:ktem.index.file.pipelines:Skip retrieval because of no selected files: DocumentRetrievalPipeline(
(vector_retrieval): <function Function.prepare_child..exec at 0x0000024B5C076EF0>
(embedding): <function Function.prepare_child..exec at 0x0000024B5C0771C0>
)
INFO:httpx:HTTP Request: POST http://127.0.0.1:5678/v1/embeddings "HTTP/1.1 200 OK"
GraphRAG embedding dim 3584
INFO:nano-graphrag:Load KV full_docs with 0 data
INFO:nano-graphrag:Load KV text_chunks with 0 data
INFO:nano-graphrag:Load KV llm_response_cache with 438 data
INFO:nano-graphrag:Load KV community_reports with 0 data
INFO:nano-graphrag:Loaded graph from E:\AI\LLM\kotaemon-NanoGraphRAG\ktem_app_data\user_data\files\nano_graphrag\8983c848-526b-4783-a255-c0115fed6e63\input\graph_chunk_entity_relation.graphml with 1772 nodes, 1127 edges
INFO:nano-vectordb:Load (1563, 3584) data
INFO:nano-vectordb:Init {'embedding_dim': 3584, 'metric': 'cosine', 'storage_file': 'E:\AI\LLM\kotaemon-NanoGraphRAG\ktem_app_data\user_data\files\nano_graphrag\8983c848-526b-4783-a255-c0115fed6e63\input\vdb_entities.json'} 1563 data
INFO:httpx:HTTP Request: POST http://127.0.0.1:5678/v1/embeddings "HTTP/1.1 200 OK"
Traceback (most recent call last):
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\queueing.py", line 575, in process_events
response = await route_utils.call_process_api(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\route_utils.py", line 276, in call_process_api
output = await app.get_blocks().process_api(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\blocks.py", line 1923, in process_api
result = await self.call_function(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\blocks.py", line 1520, in call_function
prediction = await utils.async_iteration(iterator)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 663, in async_iteration
return await iterator.anext()
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 656, in anext
return await anyio.to_thread.run_sync(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\anyio_backends_asyncio.py", line 2441, in run_sync_in_worker_thread
return await future
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\anyio_backends_asyncio.py", line 943, in run
result = context.run(func, *args)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 639, in run_sync_iterator_async
return next(iterator)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 801, in gen_wrapper
response = next(iterator)
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\pages\chat_init.py", line 981, in chat_fn
for response in pipeline.stream(chat_input, conversation_id, chat_history):
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\reasoning\simple.py", line 535, in stream
docs, infos = self.retrieve(message, history)
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\reasoning\simple.py", line 130, in retrieve
retriever_docs = retriever_node(text=query)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\base.py", line 1097, in call
raise e from None
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\base.py", line 1088, in call
output = self.fl.exec(func, args, kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\backends\base.py", line 151, in exec
return run(*args, **kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\middleware.py", line 144, in call
raise e from None
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\middleware.py", line 141, in call
output = self.next_call(*args, **kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\middleware.py", line 117, in call
return self.next_call(*args, **kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\base.py", line 1017, in runx
return self.run(*args, **kwargs)
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\index\file\graph\nano_pipelines.py", line 385, in run
entities, relationships, reports, sources = asyncio.run(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\asyncio\runners.py", line 44, in run
return loop.run_until_complete(main)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\asyncio\base_events.py", line 649, in run_until_complete
return future.result()
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\index\file\graph\nano_pipelines.py", line 155, in nano_graph_rag_build_local_query_context
use_communities = await find_most_related_community_from_entities(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\nano_graphrag_op.py", line 698, in find_most_related_community_from_entities
related_community_keys = sorted(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\nano_graphrag_op.py", line 702, in
related_community_datas[k]["report_json"].get("rating", -1),
KeyError: '2'
Session reasoning type simple use mindmap (default) use citation inline language (default)
Session LLM saiga
Reasoning class <class 'ktem.reasoning.simple.FullQAPipeline'>
Reasoning state {'app': {'regen': False}, 'pipeline': {}}
Thinking ...
Retrievers [DocumentRetrievalPipeline(DS=<kotaemon.storages.docstores.lancedb.LanceDBDocumentStore object at 0x0000024B571F0F40>, FSPath=WindowsPath('E:/AI/LLM/kotaemon-NanoGraphRAG/ktem_app_data/user_data/files/index_1'), Index=<class 'ktem.index.file.index.IndexTable'>, Source=<class 'ktem.index.file.index.Source'>, VS=<kotaemon.storages.vectorstores.chroma.ChromaVectorStore object at 0x0000024B571F00A0>, get_extra_table=False, llm_scorer=LLMTrulensScoring(concurrent=True, normalize=10, prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x0000024B538D7B50>, system_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x0000024B538D5090>, top_k=3, user_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x0000024B538D59F0>), mmr=False, rerankers=[CohereReranking(cohere_api_key='', model_name='rerank-multilingual-v2.0')], retrieval_mode='hybrid', top_k=10, user_id=1), GraphRAGRetrieverPipeline(DS=<theflow.base.unset object at 0x0000024B636A1D50>, FSPath=<theflow.base.unset object at 0x0000024B636A1D50>, Index=<class 'ktem.index.file.index.IndexTable'>, Source=<theflow.base.unset object at 0x0000024B636A1D50>, VS=<theflow.base.unset object at 0x0000024B636A1D50>, file_ids=[], user_id=<theflow.base.unset object at 0x0000024B636A1D50>), DocumentRetrievalPipeline(DS=<kotaemon.storages.docstores.lancedb.LanceDBDocumentStore object at 0x0000024B574712D0>, FSPath=WindowsPath('E:/AI/LLM/kotaemon-NanoGraphRAG/ktem_app_data/user_data/files/index_3'), Index=<class 'ktem.index.file.index.IndexTable'>, Source=<class 'ktem.index.file.index.Source'>, VS=<kotaemon.storages.vectorstores.chroma.ChromaVectorStore object at 0x0000024B57472C50>, get_extra_table=False, llm_scorer=LLMTrulensScoring(concurrent=True, normalize=10, prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x0000024B538D59C0>, system_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x0000024B5393D240>, top_k=3, user_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x0000024B5393EC50>), mmr=False, rerankers=[CohereReranking(cohere_api_key='', model_name='rerank-multilingual-v2.0')], retrieval_mode='hybrid', top_k=10, user_id=1), NanoGraphRAGRetrieverPipeline(DS=<theflow.base.unset object at 0x0000024B636A1D50>, FSPath=<theflow.base.unset object at 0x0000024B636A1D50>, Index=<class 'ktem.index.file.index.IndexTable'>, Source=<theflow.base.unset_ object at 0x0000024B636A1D50>, VS=<theflow.base.unset_ object at 0x0000024B636A1D50>, file_ids=['a1a001b8-0d74-4fb3-b208-cd57fdde2db6'], user_id=<theflow.base.unset_ object at 0x0000024B636A1D50>)]
searching in doc_ids []
INFO:ktem.index.file.pipelines:Skip retrieval because of no selected files: DocumentRetrievalPipeline(
(vector_retrieval): <function Function._prepare_child..exec at 0x0000024B5D3D24D0>
(embedding): <function Function._prepare_child..exec at 0x0000024B5D3D2710>
)
searching in doc_ids []
INFO:ktem.index.file.pipelines:Skip retrieval because of no selected files: DocumentRetrievalPipeline(
(vector_retrieval): <function Function._prepare_child..exec at 0x0000024B593CFEB0>
(embedding): <function Function.prepare_child..exec at 0x0000024B5D5CBBE0>
)
INFO:httpx:HTTP Request: POST http://127.0.0.1:5678/v1/embeddings "HTTP/1.1 200 OK"
GraphRAG embedding dim 3584
INFO:nano-graphrag:Load KV full_docs with 0 data
INFO:nano-graphrag:Load KV text_chunks with 0 data
INFO:nano-graphrag:Load KV llm_response_cache with 438 data
INFO:nano-graphrag:Load KV community_reports with 0 data
INFO:nano-graphrag:Loaded graph from E:\AI\LLM\kotaemon-NanoGraphRAG\ktem_app_data\user_data\files\nano_graphrag\8983c848-526b-4783-a255-c0115fed6e63\input\graph_chunk_entity_relation.graphml with 1772 nodes, 1127 edges
INFO:nano-vectordb:Load (1563, 3584) data
INFO:nano-vectordb:Init {'embedding_dim': 3584, 'metric': 'cosine', 'storage_file': 'E:\AI\LLM\kotaemon-NanoGraphRAG\ktem_app_data\user_data\files\nano_graphrag\8983c848-526b-4783-a255-c0115fed6e63\input\vdb_entities.json'} 1563 data
INFO:httpx:HTTP Request: POST http://127.0.0.1:5678/v1/embeddings "HTTP/1.1 200 OK"
Traceback (most recent call last):
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\queueing.py", line 575, in process_events
response = await route_utils.call_process_api(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\route_utils.py", line 276, in call_process_api
output = await app.get_blocks().process_api(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\blocks.py", line 1923, in process_api
result = await self.call_function(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\blocks.py", line 1520, in call_function
prediction = await utils.async_iteration(iterator)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 663, in async_iteration
return await iterator.anext()
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 656, in anext
return await anyio.to_thread.run_sync(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\anyio_backends_asyncio.py", line 2441, in run_sync_in_worker_thread
return await future
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\anyio_backends_asyncio.py", line 943, in run
result = context.run(func, *args)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 639, in run_sync_iterator_async
return next(iterator)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\gradio\utils.py", line 801, in gen_wrapper
response = next(iterator)
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\pages\chat_init.py", line 981, in chat_fn
for response in pipeline.stream(chat_input, conversation_id, chat_history):
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\reasoning\simple.py", line 287, in stream
docs, infos = self.retrieve(message, history)
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\reasoning\simple.py", line 130, in retrieve
retriever_docs = retriever_node(text=query)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\base.py", line 1097, in call
raise e from None
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\base.py", line 1088, in call
output = self.fl.exec(func, args, kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\backends\base.py", line 151, in exec
return run(*args, **kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\middleware.py", line 144, in call
raise e from None
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\middleware.py", line 141, in call
_output = self.next_call(*args, **kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\middleware.py", line 117, in call
return self.next_call(*args, **kwargs)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\theflow\base.py", line 1017, in _runx
return self.run(*args, **kwargs)
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\index\file\graph\nano_pipelines.py", line 385, in run
entities, relationships, reports, sources = asyncio.run(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\asyncio\runners.py", line 44, in run
return loop.run_until_complete(main)
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\asyncio\base_events.py", line 649, in run_until_complete
return future.result()
File "E:\AI\LLM\kotaemon\libs\ktem\ktem\index\file\graph\nano_pipelines.py", line 155, in nano_graph_rag_build_local_query_context
use_communities = await _find_most_related_community_from_entities(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\nano_graphrag_op.py", line 698, in _find_most_related_community_from_entities
related_community_keys = sorted(
File "E:\CondaEnvironments\kotaemon-nanographrag_env\lib\site-packages\nano_graphrag_op.py", line 702, in
related_community_datas[k]["report_json"].get("rating", -1),
KeyError: '8'

[RoadToNowhereX]

Error: Expecting property name enclosed in double quotes