Skip to content

feat: Qdrant vector store support#303

Merged
thinkall merged 26 commits into
microsoft:mainfrom
Anush008:qdrant-retriever
Oct 25, 2023
Merged

feat: Qdrant vector store support#303
thinkall merged 26 commits into
microsoft:mainfrom
Anush008:qdrant-retriever

Conversation

@Anush008

@Anush008 Anush008 commented Oct 19, 2023

Copy link
Copy Markdown

Why are these changes needed?

This PR intends to add the QdrantRetrieveUserProxyAgent class that extends RetrieveUserProxyAgent with Qdrant support.

Related issue number

Resolves #253.

Checks

  • I've included any doc changes needed for https://microsoft.github.io/autogen/.
  • I've added tests (if relevant) corresponding to the changes introduced in this PR.
  • I've made sure all auto checks have passed.

cc @thinkall.

@Anush008

Copy link
Copy Markdown
Author

@microsoft-github-policy-service agree company="Qdrant"

@qingyun-wu

Copy link
Copy Markdown
Contributor

Nice PR. Can you add a notebook demonstrating how to use this QdrantRetrieveUserProxyAgent and the example output? Thank you!

@Anush008

Anush008 commented Oct 20, 2023

Copy link
Copy Markdown
Author

Nice PR. Can you add a notebook demonstrating how to use this QdrantRetrieveUserProxyAgent and the example output? Thank you!

Sure. I'll do that.

It's here. 59e515d.

@thinkall thinkall left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you very much! @Anush008 .Very nice PR.

Comment thread autogen/agentchat/contrib/qdrant_retrieve_user_proxy_agent.py Outdated
Comment thread autogen/agentchat/contrib/qdrant_retrieve_user_proxy_agent.py Outdated
Comment thread test/agentchat/test_qdrant_retrievechat.py
Comment thread notebook/agentchat_qdrant_RetrieveChat.ipynb
Co-authored-by: Li Jiang <bnujli@gmail.com>
@VALilly

VALilly commented Oct 29, 2023

Copy link
Copy Markdown

Hello,

I am trying to use this feature to do QA for already embedded (distillbert) context in Qdrant.
But it seems only a handful of models are supported by fastembed which is probably why i am getting below error even when i speciy the embedding_model parameter as distillbert.
'UnexpectedResponse: Unexpected Response: 400 (Bad Request)
Raw response content:
b'{"status":{"error":"Wrong input: Vector params for fast-bge-small-en are not specified in config"},"time":'
Could you confirm if this is the reason for the error and if there is potential to extend the supported models?

@Anush008

Copy link
Copy Markdown
Author

But it seems only a handful of models are supported by fastembed which is probably why i am getting below error even when i speciy the embedding_model parameter as distillbert.
'UnexpectedResponse: Unexpected Response: 400 (Bad Request)
Raw response content:
b'{"status":{"error":"Wrong input: Vector params for fast-bge-small-en are not specified in config"},"time":'
Could you confirm if this is the reason for the error and if there is potential to extend the supported models?

Yes. You can find the list of supported models here.

https://qdrant.github.io/fastembed/examples/Supported_Models/

@thinkall thinkall mentioned this pull request Nov 18, 2023
3 tasks
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

Successfully merging this pull request may close these issues.

Qdrant Vectorstore Support

6 participants