fix(ai): 법률 RAG 답변 LLM 호출 연결 - #31
Merged
Merged
Conversation
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
📝 WalkthroughWalkthrough
ChangesLive Legal LLM Integration
Sequence DiagramsequenceDiagram
participant Client
participant LLMClient
participant _generate_live
participant HTTPPost
participant LLMEndpoint as OpenAI /chat/completions
participant extract
Client->>LLMClient: generate_answer(state, Intent.LEGAL_CONSULT)
LLMClient->>_generate_live: state
alt Config present (base_url, model, api_key)
_generate_live->>HTTPPost: POST {base_url}/chat/completions<br/>Bearer auth, RAG prompt
HTTPPost->>LLMEndpoint: HTTP request with model/message
LLMEndpoint-->>HTTPPost: JSON choices[0].message
HTTPPost-->>_generate_live: Response
_generate_live->>extract: response payload
extract-->>_generate_live: text or None
_generate_live-->>LLMClient: text or None
else Missing config or HTTP error
_generate_live-->>LLMClient: None
end
alt Live result present
LLMClient-->>Client: text answer
else Fallback path
LLMClient->>LLMClient: generate_legal_answer(state)
LLMClient-->>Client: fallback answer
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
backend-ai/tests/test_legal_answer_generation.py (1)
121-138: 🧹 Nitpick | 🔵 Trivial | ⚡ Quick winAdd a malformed-payload regression test for extractor fallback
Current coverage validates text-part extraction but not malformed payload shapes. Add a non-dict payload case to lock in
Nonebehavior and prevent future fallback regressions.Suggested test addition
def test_extract_chat_completion_text_supports_text_parts() -> None: assert ( extract_chat_completion_text( { "choices": [ { "message": { "content": [ {"type": "text", "text": "첫 문장"}, {"type": "output_text", "text": "둘째 문장"}, ] } } ] } ) == "첫 문장\n둘째 문장" ) + + +def test_extract_chat_completion_text_returns_none_for_non_object_payload() -> None: + assert extract_chat_completion_text([]) is None🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@backend-ai/tests/test_legal_answer_generation.py` around lines 121 - 138, Add a regression test for malformed payload handling in the extract_chat_completion_text function to ensure the fallback behavior is locked in. Create a new test function (e.g., test_extract_chat_completion_text_handles_malformed_payload) that passes various malformed payload shapes to extract_chat_completion_text (such as non-dict payloads, missing required fields, or other invalid structures) and asserts that the function returns None gracefully to prevent future regressions in the extractor fallback logic.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@backend-ai/app/clients/llm_client.py`:
- Around line 92-95: The function `extract_chat_completion_text` calls `.get()`
on the `payload` parameter without first verifying it is a dictionary. Add a
guard clause at the beginning of the function to check if `payload` is an
instance of dict using `isinstance(payload, dict)`, and return None if it is
not, before attempting to call `.get("choices")` on it. This will prevent
`AttributeError` when the provider returns a non-dict JSON payload.
---
Nitpick comments:
In `@backend-ai/tests/test_legal_answer_generation.py`:
- Around line 121-138: Add a regression test for malformed payload handling in
the extract_chat_completion_text function to ensure the fallback behavior is
locked in. Create a new test function (e.g.,
test_extract_chat_completion_text_handles_malformed_payload) that passes various
malformed payload shapes to extract_chat_completion_text (such as non-dict
payloads, missing required fields, or other invalid structures) and asserts that
the function returns None gracefully to prevent future regressions in the
extractor fallback logic.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 65983b29-7586-4883-9735-c2e9f1c52e11
📒 Files selected for processing (4)
backend-ai/app/clients/llm_client.pybackend-ai/app/core/config.pybackend-ai/tests/conftest.pybackend-ai/tests/test_legal_answer_generation.py
2 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
변경 내용
원인
테스트
closes #30
Summary by CodeRabbit
llm_base_urlsetting (with environment override) for controlling the LLM API endpoint.