MongoDB + new abstraction of vectordb

[ranfysvalle02]

Why are these changes needed?

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.

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!
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.
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: 711

Closes #711

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.

[ranfysvalle02]

@microsoft-github-policy-service agree

[ranfysvalle02]

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

[Josephrp]

nice addition, it would be nice with an example, and in my opinion it would also be nice with an "advanced example" because it appears to be possible to also use mongodb on cloud services for example cosmosdb on azure :-)

[Jibola]

Thanks for putting up this PR. Looks great and is helpful for us!

I've added some suggestions around implementation details, but overall it's a solid PR. Let me know what you think.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 0% with 114 lines in your changes missing coverage. Please review.

Project coverage is 15.71%. Comparing base (bf7e4d6) to head (5972fd0).
Report is 16 commits behind head on main.

Files	Patch %	Lines
autogen/agentchat/contrib/vectordb/mongodb.py	0.00%	111 Missing ⚠️
autogen/agentchat/contrib/vectordb/base.py	0.00%	3 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #2942       +/-   ##
===========================================
- Coverage   33.99%   15.71%   -18.29%     
===========================================
  Files          89       90        +1     
  Lines        9593     9719      +126     
  Branches     2054     2242      +188     
===========================================
- Hits         3261     1527     -1734     
- Misses       6057     8142     +2085     
+ Partials      275       50      -225     

Flag	Coverage Δ
unittests	15.67% <0.00%> (-18.33%)	⬇️

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.

[thinkall]

Thank you very much for the PR, @ranfysvalle02 !
Could you provide an example of how to set up a mongodb in local? You could refer to https://github.com/microsoft/autogen/blob/main/notebook/agentchat_pgvector_RetrieveChat.ipynb

Could you also update the dependencies in setup.py?

[thinkall]

To fix the code formatting issue:

pip install pre-commit
pre-commit run --show-diff-on-failure --color=always --all-files

[ranfysvalle02]

Will be working on the feedback received from this thread as well as internally from MongoDB. I'll update the PR soon

[ranfysvalle02]

I think I got most of the feedback in @thinkall @Jibola - let me know what you think

[ranfysvalle02]

There are some issues with the tests --- working them out now.

[thinkall]

Hi @ranfysvalle02 , the format issue still exists. Please let me know once it's ready for review. Thanks.

[ranfysvalle02]

@thinkall @Jibola I think this PR is ready for another look whenever you guys have the chance

[ranfysvalle02]

code has been updated ;)

[ranfysvalle02]

It keeps showing "one change requested", but I'm not sure what this one is about @Hk669 -- Let me know if I covered it with the code update or if there is anything else I should change

[Hk669]

looks good to me. if the comments are addressed. thanks @ranfysvalle02 for your contribution

[Hk669]

@ranfysvalle02 can you run the pre-commit to fix the formatting.

[Hk669]

@thinkall can you please review the PR.

[ranfysvalle02]

pre-commit run --show-diff-on-failure --color=always --all-files

Fixed the formatting issue! thanks @Hk669

@thinkall let me know if there is anything else that needs work, I have some availability today to get this knocked out :)

[gitguardian]

⚠️ GitGuardian has uncovered 1 secret following the scan of your pull request.

Please consider investigating the findings and remediating the incidents. Failure to do so may lead to compromising the associated services or software components.

🔎 Detected hardcoded secret in your pull request

GitGuardian id	GitGuardian status	Secret	Commit	Filename
10404662	Triggered	Generic CLI Secret	c44c8bd	.github/workflows/dotnet-build.yml	View secret

🛠 Guidelines to remediate hardcoded secrets

1. Understand the implications of revoking this secret by investigating where it is used in your code.
2. Replace and store your secret safely. Learn here the best practices.
3. Revoke and rotate this secret.
4. If possible, rewrite git history. Rewriting git history is not a trivial act. You might completely break other contributing developers' workflow and you risk accidentally deleting legitimate data.

To avoid such incidents in the future consider

• following these best practices for managing and storing secrets including API keys and other credentials
• install secret detection on pre-commit to catch secret before it leaves your machine and ease remediation.

---

^{🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.}

[thinkall]

Hi @ranfysvalle02 , I still see ConfigurationError: The DNS query name does not exist: _mongodb._tcp.shared.demo.mongodb.net..

[ranfysvalle02]

I have updated the notebook -- I think this will do it :)

[thinkall]

This mongodb://username:password@localhost/?directConnection=true worked for me. Then I see:

1. Trying to create collection.
   2024-06-21 21:44:25,912 - autogen.agentchat.contrib.retrieve_user_proxy_agent - INFO - Found 2 chunks.
   VectorDB returns doc_ids: [[]]
   Which means retrieve_docs doesn't work as expected.

2. ValueError: Collection flaml_collection_two already exists. which means overwrite=True doesn't work as expected.

[thinkall]

@ranfysvalle02 If you run pre-commit install you should get auto code formatting before you make a commit.

[ranfysvalle02]

@ranfysvalle02 If you run pre-commit install you should get auto code formatting before you make a commit.

I will be better about this one sorry :)

[ranfysvalle02]

@thinkall @Jibola @Hk669

We're getting closer! Would appreciate any help getting this down the line! Let me know what else needs to be updated! Going to disconnect for a while but will try to get back on this evening. Excited to get MongoDB into Autogen :)

[ranfysvalle02]

Sorry guys!!!!! Here is the new Pull Request with a fresh commit history... Did a lot of learning here :)

#2996