PDF files contain no data in RAG

[frenzybiscuit]

Basically, title.

I just updated, so on the latest version at this moment.

docker images | grep librechat
ghcr.io/danny-avila/librechat-dev latest c83689215440 51 minutes ago 882MB
ghcr.io/danny-avila/librechat-dev e4979ae60fba 36 hours ago 866MB
ghcr.io/danny-avila/librechat-rag-api-dev latest 5f0a3f475b72 12 days ago 7.79GB
ghcr.io/danny-avila/librechat-rag-api-dev-lite latest 6550e7ddf180 12 days ago 1.3GB

RAG .env setup (no docker for ollama. Librechat is in a docker.):

RAG_API_URL=http://host.docker.internal:8000
EMBEDDINGS_PROVIDER=ollama
OLLAMA_BASE_URL=http://192.168.11.1:11434
#EMBEDDINGS_MODEL=mxbai-embed-large
EMBEDDINGS_MODEL=nomic-embed-text
CHUNK_SIZE=3000
CHUNK_OVERLAP=100
RAG_USE_FULL_CONTEXT=False

The docker-compose.override is setup as well.

Ollama spikes to 100% of a core when the pdf is uploaded, but its brief.

It is able to view the metadata of the pdf file, and it can tell me about that, but it is not able to view and tell me about the actual content of the PDF file.

[marlonka]

is your pdf file an image or machine readable text?