🚀 feat: Add Qdrant Vector Database

[walbercardoso]

Add qdrant vector store to improve vectors database

[walbercardoso]

For some functions it is not necessary to use run_in_executor, since there are async functions in langchain for qdrant.

[walbercardoso]

@danny-avila I would appreciate it if you could take a look at the implementation and let me know if everything is ok.

[walbercardoso]

New variables need to be add at the .env

QDRANT_API_KEY=

QDRANT_HOST=

VECTOR_DB= #qdrant or pgvector (default if not `provided)` 

COLLECTION_NAME=

EMBEDDINGS_DIMENSION=

[walbercardoso]

Can you please check this if it need some change? If it's ok I'm planning to add other vector stores

[danny-avila]

there are some conflicts due to the mongodb atlas merge

[walbercardoso]

No problem. I can fix that.

[walbercardoso]

@danny-avila Conflicts removed. Can you check it again?

[danny-avila]

@danny-avila Conflicts removed. Can you check it again?

hi @walbercardoso there are some new conflicts. I've added enums to help manage the addition of vector stores. Also, I would like to see all routes working with screenshots and configuration settings for your setup, because the last addition of a vector store does not seem fully functional.

Thanks

[walbercardoso]

hi @danny-avila . Conflicts have been fixed.

Some screenshots:

Embed:

Route

Qdrant dash:

Delete attach file before starting query:

Route:

Query doc:

Route:

Delete file:

Route:

[walbercardoso]

Configuration params at .env

QDRANT_API_KEY=

QDRANT_HOST=""

VECTOR_DB_TYPE="qdrant"

QDRANT_VECTOR_COLLECTION="test"

QDRANT_EMBEDDINGS_DIMENSION=768

[walbercardoso]

Please let me know if this is enough

[danny-avila]

Replacing with https://github.com/danny-avila/rag_api/pull/73