Connor Finn
Connor Finn
Moved over to #86
Looked into implementing [qdrant async client](https://qdrant.tech/documentation/tutorials/async-api/) Would we still want to retain support for sync qdrant? Would restructure code that we have, but have two separate vector-DB.
@jerowe Are you still having the issue? One thing I would check is to ensure that the file embedding is actually stored in whatever vector database you are using (pgvector...
Have not tested with ollama yet.
Missing dependency of `langchain-ollama=0.2.0` seems to be the reason. Thanks @sreevatsank1999 for pointing this out. I added it to `requirements.lite.txt` #85
IDs per vector assigned as `(file_id)_#` . Using a prefix `file_id` with numbering `0,1,2,...`. Should not affect naming `file_id` able to include '_' in `file_id` such that read `my_file_0`
Ideal `BATCH_SIZE` varies on embeddings provider and likely model and file size. Specific default values should be added per embeddings provider in future. Right now the default for `BATCH_SIZE=75` which...
@JulianHandrup thanks for bringing this up. Added relevant env variables here #97
I tested with `CHUNK_SIZE=1500` `EMBEDDINGS_PROVIDER=bedrock` `EMBEDDINGS_MODEL=amazon.titan-embed-text-v1` `PDF_EXTRACT_IMAGES=False`. I was unable to to see any issue with indexing this pdf (5 MB) and querying in both with docker and with only...
@dirkpetersen were you able to get RAG API to work?