Cinnamon / kotaemon

An open-source RAG-based tool for chatting with your documents.
https://cinnamon.github.io/kotaemon/
Apache License 2.0
17.49k stars 1.35k forks source link

[BUG] LightRAG retriever finds no documents #516

Open milsun opened 1 day ago

milsun commented 1 day ago

Description

i tried indexing few pdfs for LightRAG, indexing works successfully, at least based on the logs, but when I try to chat about the data, no matter the question, is always returns 0 documents found.

When I select "Search All" under LightRAG Collection, it says 0 documents found, and when I select the indexed file using "Search in FIle(s)", it throws an error.

Reproduction steps

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Screenshots

![DESCRIPTION](LINK.png)

Logs

Retrievers [DocumentRetrievalPipeline(DS=<kotaemon.storages.docstores.lancedb.LanceDBDocumentStore object at 0x30fc5f310>, FSPath=PosixPath('/Users/milan/Desktop/ai/rag/kotaemon/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 0x30fc5f6a0>, get_extra_table=False, llm_scorer=LLMTrulensScoring(concurrent=True, normalize=10, prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x1779f8460>, system_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x1779f9cc0>, top_k=3, user_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x1779f9570>), 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 0x1027f9ff0>, FSPath=<theflow.base.unset_ object at 0x1027f9ff0>, Index=<class 'ktem.index.file.index.IndexTable'>, Source=<theflow.base.unset_ object at 0x1027f9ff0>, VS=<theflow.base.unset_ object at 0x1027f9ff0>, file_ids=[], user_id=<theflow.base.unset_ object at 0x1027f9ff0>), LightRAGRetrieverPipeline(DS=<theflow.base.unset_ object at 0x1027f9ff0>, FSPath=<theflow.base.unset_ object at 0x1027f9ff0>, Index=<class 'ktem.index.file.index.IndexTable'>, Source=<theflow.base.unset_ object at 0x1027f9ff0>, VS=<theflow.base.unset_ object at 0x1027f9ff0>, file_ids=[], user_id=<theflow.base.unset_ object at 0x1027f9ff0>)]
searching in doc_ids []
INFO:ktem.index.file.pipelines:Skip retrieval because of no selected files: DocumentRetrievalPipeline(
  (vector_retrieval): <function Function._prepare_child.<locals>.exec at 0x177a26290>
  (embedding): <function Function._prepare_child.<locals>.exec at 0x177a277f0>
)
Got 0 retrieved documents
len (original) 0
Got 0 images
File "/Users/milan/Desktop/ai/rag/kotaemon/libs/ktem/ktem/index/file/graph/lightrag_pipelines.py", line 140, in lightrag_build_local_query_context
    raise ValueError("No results found")
ValueError: No results found

Browsers

Chrome

OS

MacOS

Additional information

No response