CogniSwitch Integration

[CogniJT]

Added Components

• QueryEngine
• Tests
• Example Notebook
• Inits

Description

This provides a connector to the CogniSwitch platform within LlamaIndex.

What is CogniSwitch?

CogniSwitch enhances the reliability of Generative AI applications for enterprises. It achieves this by leveraging AI to gather and organize knowledge from documented sources, eliminating biases and hallucinations in AI responses. The platform allows experts to curate and visualize this knowledge before it is published. The CogniSwitch API enables Gen AI applications to access this knowledge as needed, ensuring reliability. It seamlessly integrates with top Generative AI technologies and offers customized solutions for different business functions within an enterprise.

Why CogniSwitch?

Use CogniSwitch to build production ready applications that can consume, organize and retrieve knowledge flawlessly. Using the framework of your choice, in this case Llama-Index, CogniSwitch helps alleviate the stress of decision making when it comes to, choosing the right storage and retrieval formats. It also eradicates reliability issues and hallucinations when it comes to responses that are generated. Get started by interacting with your knowledge in just three simple steps

Type of Change

• New feature (non-breaking change which adds functionality)

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

• Added new unit/integration tests
• Added new notebook (that tests end-to-end)
• I stared at the code and made sure it makes sense

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[jerryjliu]

thanks! let's keep the cogniswitch query engine part here, for the tool spec could you submit to llama-hub instead? we're centralizing all integrations there https://github.com/run-llama/llama-hub

[CogniJT]

Thanks for the response & guidance @jerryjliu

Will remove the tool spec & update the pull request accordingly.

[CogniJT]

Hi @jerryjliu, created a related PR in LlamaHub. That would be a dependency in order for this to work. Could you streamline that please?

[CogniJT]

run-llama/llama-hub#604

[CogniJT]

Hi @jerryjliu, made the changes as you requested. We are now merged with LlamaHub & using that import over here. Do take a look & let us know if anything else is required. Thanks!

[Disiok]

Hi @jerryjliu, made the changes as you requested. We are now merged with LlamaHub & using that import over here. Do take a look & let us know if anything else is required. Thanks!

Thanks for the great work! Taking a look to merge this.

[Disiok]

Hey @CogniJT could you allow maintainers to push to the branch? Just want to push some cleanup fixes before I merge the PR.

[saiCogniswitch]

hey @Disiok, can you let us know if there is any bug in the code?

[CogniJT]

Hi @Disiok, as far I can see there does not seem to be any restrictions in settings. Perhaps you're talking about the llama_index repo access? We don't have permissions to change that. As part of your review, could you leave your comments for changes & we can follow through on those. Thanks!

[CogniJT]

@jerryjliu could you please clarify what's required to move ahead? Thank you.

[CogniJT]

Just a heads up that we've updated the BaseQueryEngine to its new form subclassing PromptMixin

[saiCogniswitch]

hi @jerryjliu I was checking the above checks where linting failed, but in the codespaces from my side the lint had passed successfully, can you please let us know how to resolve this and move forward. Thanks!
have a good day.

[Disiok]

Hey folks, looks like lint is still failing. could you pull the latest main, and make sure you have the pre-commit hooks installed? Thanks!

Also it'd be really helpful to allow us to make changes to your branch, so we can quickly fix stuff up on our side. Take a look at https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/allowing-changes-to-a-pull-request-branch-created-from-a-fork to see if this is possible.

[CogniJT]

Thanks @Disiok, the link clarifies what you were asking for. However I'm unable to find the below option under this Pull Request

On user-owned forks, if you want to allow anyone with push access to the upstream repository to make changes to your pull request, select Allow edits from maintainers.
Perhaps because this isn't user-owned?

@saiCogniswitch could you look into the linting issues

[saiCogniswitch]

hi @Disiok , so I have run the lint with pre-commit hooks installed and the lint has run successfully in the codespaces, currently I have updated the changes accordingly. Let me know if if there is something else that can be done to check the lint thanks.
have a good day.

[Disiok]

Hey folks, here's the specific lint issue:

pre-commit hook(s) made changes.
If you are seeing this message in CI, reproduce locally with: `pre-commit run --all-files`.
To run `pre-commit` as part of git workflow, use `pre-commit install`.
All changes made by hooks:
diff --git a/llama_index/query_engine/cogniswitch_query_engine.py b/llama_index/query_engine/cogniswitch_query_engine.py
index a90d84b..baaa3[69](https://github.com/run-llama/llama_index/actions/runs/6753676283/job/18381073099?pr=8466#step:6:70) 100644
--- a/llama_index/query_engine/cogniswitch_query_engine.py
+++ b/llama_index/query_engine/cogniswitch_query_engine.py
@@ -4,7 +4,7 @@ import requests
 
 from llama_index.indices.query.base import BaseQueryEngine
 from llama_index.indices.query.schema import QueryBundle
-from llama_index.response.schema import RESPONSE_TYPE, Response
+from llama_index.response.schema import Response
 
 
 class CogniswitchQueryEngine(BaseQueryEngine):
diff --git a/tests/query_engine/test_cogniswitch_query_engine.py b/tests/query_engine/test_cogniswitch_query_engine.py
index 399f[79](https://github.com/run-llama/llama_index/actions/runs/6753676283/job/18381073099?pr=8466#step:6:80)3..[84](https://github.com/run-llama/llama_index/actions/runs/6753676283/job/18381073099?pr=8466#step:6:85)2f4d8 100644
--- a/tests/query_engine/test_cogniswitch_query_engine.py
+++ b/tests/query_engine/test_cogniswitch_query_engine.py
@@ -1,5 +1,5 @@
 from typing import Any
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 import pytest
 from llama_index.query_engine.cogniswitch_query_engine import CogniswitchQueryEngine
make: *** [Makefile:11: lint] Error 1
Error: Process completed with exit code 2.

[saiCogniswitch]

hi @Disiok , thanks for sharing the lint issue, the changes it is showing in the w.r.t the python file name, the change is same for the both "cogniswitch_query_engine.py" and "test_cogniswitch_query_engine.py". Do we have to do something w.r.t that?
I have also removed the unnecessary imports and updated it. Can you check and let us know if now is it ok.
Have a good day.

[saiCogniswitch]

Hi @jerryjliu
Good Morning
just bumping this up for approval and merge, let us know if anything is required from us.
Thanks , have a good day

[Disiok]

Thanks for the updates! Looks like it's passing CI now.

[saiCogniswitch]

Thanks @Disiok for the approval and merge.

[CogniJT]

Thanks @Disiok & @jerryjliu for all your help

[CogniJT]

@Disiok Would the examples we shared in this PR go into doc.llamaindex.ai?