Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

After setting up PGVector local_data is still being written (0.40) #1688

Closed
HenrikPedDK opened this issue Mar 7, 2024 · 2 comments
Closed

Comments

@HenrikPedDK
Copy link

I did a total fresh install (again) using ollama, connect to postgres and tested a few ingestions. I see that the ingestion is feeding into the DB but it is also building a big JSON in local_data:

-rw-rw-r-- 1 develop develop 9946 Mar 7 10:23 docstore.json
-rw-rw-r-- 1 develop develop 18 Mar 7 10:23 graph_store.json
-rw-rw-r-- 1 develop develop 72 Mar 7 10:23 image__vector_store.json
-rw-rw-r-- 1 develop develop 667 Mar 7 10:23 index_store.json
(base) develop@gpt:~/privateGPT/local_data/private_gpt$

settings-ollama.yaml:

ollama:
llm_model: mistral
embedding_model: nomic-embed-text
api_base: http://localhost:11434/

vectorstore:
database: pgvector

pgvector:
host: 192.168.1.97
port: 5432
database: Vector
user: postgres
password: postgres
embed_dim: 768 # 384 is for BAAI/bge-small-en-v1.5
schema_name: private_gpt
table_name: embeddings

@HenrikPedDK
Copy link
Author

Also it's using the local_data for embeddings even after deleting the whole table in PG

@imartinez
Copy link
Collaborator

local_data is storing the index_store and document_store JSONs. There is a PR in progress to use Postgres as index and document store to avoid any content in local_data folder. #1706

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants