jonfairbanks/local-rag
Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.
PythonGPL-3.0
Issues
- 0
ollama - ERROR - Failed to retrieve Ollama model list: [Errno 99] Cannot assign requested address
#65 opened by maifeeulasad - 0
- 4
- 1
- 3
Streamlit cache leading to empty index
#48 opened by tinamil - 1
- 2
- 1
Error when querying the model
#51 opened by AusbelDev - 6
TypeError: Object is not an iterable and could not be converted to one. Object: False
#40 opened by RMasamune - 0
Admin page, chat page
#44 opened by solarleb - 0
No response in wsl
#50 opened by genesiz7 - 0
Object Error: TypeError
#47 opened by n0w33d - 0
exporting / reimporting of indexed data?
#35 opened by wolfspyre - 1
gitlab repos?
#34 opened by wolfspyre - 2
data directory gets destroyed after a pipeline finishes. but is expected to exist by github repo importer
#33 opened by wolfspyre - 8
seems like attempting to index a website gets llama_index to reach out to openai?
#36 opened by wolfspyre - 1
Integrate with R2R for RAG backend
#21 opened by emrgnt-cmplxty - 1
epub parser not installed automagically
#37 opened by wolfspyre - 1
Advanced Chunking Strategies
#28 opened by kedar-1 - 1
Docker compose extra host config needed?
#25 opened by kedar-1 - 5
- 4