Eugene Zapolsky 6b9e3ed9e9 google-vertexai[minor]: added safety_settings property to gemini wrapper (#15344) ...

**Description:** Gemini model has quite annoying default safety_settings
settings. In addition, current VertexAI class doesn't provide a property
to override such settings.
So, this PR aims to 
 - add safety_settings property to VertexAI
- fix issue with incorrect LLM output parsing when LLM responds with
appropriate 'blocked' response
- fix issue with incorrect parsing LLM output when Gemini API blocks
prompt itself as inappropriate
- add safety_settings related tests

I'm not enough familiar with langchain code base and guidelines. So, any
comments and/or suggestions are very welcome.
 
**Issue:** it will likely fix #14841

---------

Co-authored-by: Erick Friis <erick@langchain.dev>

2024-01-18 08:54:30 -08:00

..

cli

Make packages optional (#15727)

2024-01-08 17:09:21 -08:00

community

infra: Use dotenv in langchain-community's integration tests (#16137)

2024-01-17 18:18:26 -08:00

core

core[patch]: testing add chat model for unit-tests (#16209)

2024-01-18 11:30:53 -05:00

experimental

core[patch]: simple prompt pretty printing (#15968)

2024-01-12 21:08:51 -05:00

langchain

Add revision identifier to run_on_dataset (#16167)

2024-01-17 20:27:43 -08:00

partners

google-vertexai[minor]: added safety_settings property to gemini wrapper (#15344)

2024-01-18 08:54:30 -08:00