yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-11-30 00:46:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: forcing response format to be JSON valid (#7692)

Browse Source 
* forcing response format to be JSON valid

* adding release notes

* cleaning up

* Update haystack/components/evaluators/llm_evaluator.py

Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com>

---------

Co-authored-by: Madeesh Kannan <shadeMe@users.noreply.github.com>
This commit is contained in:
David S. Batista 2024-05-14 12:22:38 +02:00 committed by GitHub
parent a2be90b95a
commit 75cf35c743
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
haystack/components/evaluators/llm_evaluator.py
View File

@ -87,7 +87,9 @@ class LLMEvaluator:
self.api_key = api_key
if api == "openai":
self.generator = OpenAIGenerator(api_key=api_key)
self.generator = OpenAIGenerator(
api_key=api_key, generation_kwargs={"response_format": {"type": "json_object"}}
)
else:
raise ValueError(f"Unsupported API: {api}")

6
releasenotes/notes/force-valid-JSON-OpeanAI-LLM-based-evaluators-64816e68f137739b.yaml Normal file
View File

@ -0,0 +1,6 @@
---
enhancements:
- |
Enforce JSON mode on OpenAI LLM-based evaluators so that the they always return valid JSON output.
This is to ensure that the output is always in a consistent format, regardless of the input.