Create a MongoDB retrieval Agent

[cozypet]

Why are these changes needed?

Using RetrieveChat with MongoDB for Retrieve Augmented Code Generation and Question Answering

MongoDB has been ranked as the best vector database(https://www.mongodb.com/blog/post/atlas-vector-search-commands-highest-developer-nps-retool-state-ai-2023-survey) in the Retool AI report, so it is quite important to add MongoDB vector search as an option for Autogen RAG.

You can easily start the MongoDB vector search on a free tier M0 MongoDB Atlas cluster. Free tier cluster provides the full functionality of the MongoDB vector search. https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/

But why is MongoDB such a standout? Well, there are a few key reasons.

1. MongoDB Atlas integrates smoothly with existing databases. For organizations already using MongoDB, this means a seamless expansion into the vector storage—no major system overhauls required!
2. MongoDB Atlas is built to handle operational heavy-lifting. It excels when serving large-scale, mission-critical applications, offering robustness and reliability where it counts.
3. MongoDB's flexibility in handling a variety of data types and structures makes it perfectly suited to the complexity of vector embeddings.

As such, implementing MongoDB as a Retrieval Agent can unlock new potential in your AI applications, bringing the full power of vector storage to bear.

Related issue number

Checks

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

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 0% with 47 lines in your changes missing coverage. Please review.

Project coverage is 31.91%. Comparing base (140a023) to head (85cdc5a).
Report is 765 commits behind head on main.

Files	Patch %	Lines
...tchat/contrib/mongoDB_retrieve_user_proxy_agent.py	0.00%	47 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #711      +/-   ##
==========================================
+ Coverage   27.89%   31.91%   +4.01%     
==========================================
  Files          27       28       +1     
  Lines        3466     3513      +47     
  Branches      784      790       +6     
==========================================
+ Hits          967     1121     +154     
+ Misses       2428     2309     -119     
- Partials       71       83      +12     

Flag	Coverage Δ
unittests	31.82% <0.00%> (+3.98%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[cozypet]

@microsoft-github-policy-service agree [company="{}"]

[cozypet]

@microsoft-github-policy-service agree

[sonichi]

@thinkall could you advise how to write the test to avoid the build error?

[ranfysvalle02]

@sonichi @thinkall @cozypet -

I think the issue here is -- MongoDB Atlas search is 'cloud only' and cannot be run in a in the Docker environment like we do with Postgres.

.github>workflows>contrib-openai.yaml ankane/pgvector

Any suggested path forward here?

[thinkall]

@sonichi @thinkall @cozypet -

I think the issue here is -- MongoDB Atlas search is 'cloud only' and cannot be run in a in the Docker environment like we do with Postgres.

.github>workflows>contrib-openai.yaml ankane/pgvector

Any suggested path forward here?

Hi @ranfysvalle02 , we have new abstract of vectordb https://github.com/microsoft/autogen/tree/main/autogen/agentchat/contrib/vectordb . I would suggest adding a new mongodb class. No new agent is needed. Would you like to work on it?

[ranfysvalle02]

@thinkall

Here is the Pull Request: #2942

[ghost]

These are hackers hacking me please contact fbi

…

On Fri, Jun 14, 2024, 1:18 AM Fabian Valle ***@***.***> wrote: @thinkall <https://github.com/thinkall> Here is the Pull Request: #2942 <#2942> — Reply to this email directly, view it on GitHub <#711 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BI3MSTC33SLVQTSYVZ3CMALZHKDLNAVCNFSM6AAAAAA7Q3TPX2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCNRXGI4DONJWGA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>