Skip to content

Fixed documentation, testcases, new provider for LLM Chat #1350

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 19 commits into from
Oct 28, 2025
Merged

Fixed documentation, testcases, new provider for LLM Chat #1350

merged 19 commits into from
Oct 28, 2025

Conversation

@kevalmahajan
Copy link
Member

@kevalmahajan kevalmahajan commented Oct 27, 2025 •
edited
Loading

🐛 Bug-fix PR

📌 Summary

Closes #1239 and #1348

  1. Added support for IBM watsonx.ai LLM provider
  2. Added indepth documentation for LLM chat including setup, usage, architecture and more.
  3. Updated Redis configuration requirements for session persistence and chat consistency.
  4. Added integration tests for testing endpoints of LLM Chat with scenarios like multi-worker coordination, redis failure cases, chat history persistence and more.
  5. Improved configurations of env variable from settings class for consistency.

🧪 Verification

Check Command Status
Lint suite make lint Pass
Unit tests make test Pass
Coverage ≥ 90 % make coverage
Manual regression no longer fails steps / screenshots

📐 MCP Compliance (if relevant)

  • Matches current MCP spec
  • No breaking change to MCP clients

✅ Checklist

  • Code formatted (make black isort pre-commit)
  • No secrets/credentials committed

@kevalmahajan kevalmahajan marked this pull request as draft October 27, 2025 16:57
@kevalmahajan kevalmahajan marked this pull request as ready for review October 28, 2025 05:46
kevalmahajan and others added 18 commits October 28, 2025 21:14
@kevalmahajan @crivetimihai
added watsonx ai llm provider
1e4d17b 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
error handling for dependency failure
896dfb9 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
linting
4f958b4 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
documentation for LLM Chat
7fe1354 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
minor change
117ff5a 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
added redis configurations
8f8aecd 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
worker_id consistency
8ceb145 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
config env variable consistency
37e4532 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
updated redis configs
a974ccb 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
added watsonx.ai configurations
9c78120 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
doc link updated
8e2b97e 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
chat related configurations
0ae5ea1 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
linting
e47bf2e 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
remove unused import
ebd08c3 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
added integration test cases for llm chat
ec6f770 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
update doctests
0e730db 
Signed-off-by: Keval Mahajan <[email protected]>
@kevalmahajan @crivetimihai
update configurations
48d83bc 
Signed-off-by: Keval Mahajan <[email protected]>
@crivetimihai
docs: fix typos and inconsistencies in LLM Chat documentation
974e161 
- Fix typo: "tempurature" → "temperature" in README
- Fix wrong default model: "granite3b" → "ibm/granite-13b-chat-v2"
- Fix model_id type: int → string
- Fix duplicate in variable name: LLMCHAT_SESSION_SESSION_TTL → LLMCHAT_SESSION_TTL
- Fix incorrect defaults for Redis settings (CHAT_HISTORY_TTL: 0.2 → 3600, CHAT_HISTORY_MAX_MESSAGES: 0.2 → 50)
- Add missing LLMCHAT_ prefix to env vars in llm-chat.md to match config.py
- Improve table formatting for consistency

Signed-off-by: Mihai Criveti <[email protected]>
@crivetimihai crivetimihai force-pushed the add_watsonx_provider_support branch from 0d9c484 to 974e161 Compare October 28, 2025 22:18
@crivetimihai
docs: rename diagram images to descriptive, Linux-friendly names
d11c30e 
Rename documentation images from generic "Untitled diagram-*" to
descriptive names without spaces:
- Untitled diagram-2025-10-27-134134.png → llm-chat-workflow-architecture.png
- Untitled diagram-2025-10-27-134308.png → llm-chat-session-management.png

Update image references in llm-chat.md with proper alt text.

Signed-off-by: Mihai Criveti <[email protected]>
@crivetimihai crivetimihai merged commit 44ee927 into main Oct 28, 2025
45 checks passed
@crivetimihai crivetimihai deleted the add_watsonx_provider_support branch October 28, 2025 22:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@crivetimihai crivetimihai crivetimihai approved these changes

@madhav165 madhav165 Awaiting requested review from madhav165 madhav165 is a code owner

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

LLMChat Multi-Worker: Add Documentation and Integration Tests (PR #1236 Follow-up)

3 participants

@kevalmahajan @crivetimihai