Unable to Retrieve Documents by Filename After Successful Ingestion #3196
Unanswered
bibin-aplxs
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I'm using LightRAG as a knowledge base and have noticed an issue with document retrieval.
Some documents are successfully ingested and show a Completed status in the Documents tab. The generated summary also contains the document filename. However, when I query LightRAG using the exact filename, it responds that it has no information about that file.
LLM: openai gpt-4.1-nano
Embedding Model: openai text-embedding-3-small
Example
Document: INC0319069.md
Ingestion Status: Completed
Summary: Contains the filename
Query: INC0319069
Result: "I do not have enough information in the provided context to identify or provide details regarding incident INC0319069. Please provide additional details or specify the nature of your inquiry about this incident."
This does not happen for all documents, and the issue appears across multiple file types.
Questions:
Are filenames indexed for retrieval?
Does LightRAG support searching by document metadata/filename?
Is this a known limitation or a potential bug?
Any guidance would be appreciated.

Beta Was this translation helpful? Give feedback.
All reactions