-
Notifications
You must be signed in to change notification settings - Fork 317
release: 3.0.0 (langchain-v1) (genai, vertexai, community) #1194
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.
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
Conversation
stricter mypy enforcement during upgrade to 3.10 and enabling stricter type checking. `_parse_response_candidate` was already receiving (and handling) both types (via `hasattr`) but the signature only declared one
| return await _achat_with_retry(**params) | ||
|
|
||
|
|
||
| def _is_lc_content_block(part: dict) -> bool: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This seemed gratuitous
| return "type" in part | ||
|
|
||
|
|
||
| def _is_openai_image_block(block: dict) -> bool: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Use util from core instead of redefining here as the logic is the same
Co-authored-by: Mason Daugherty <[email protected]>
https://googleapis.dev/python/generativelanguage/latest/generativelanguage_v1beta/generative_service.html https://googleapis.dev/python/generativelanguage/latest/generativelanguage_v1beta/types_.html#google.ai.generativelanguage_v1beta.types.GenerateContentResponse TODO(genai) - [ ] Native use of new [server tools](langchain-ai/langchain#33021) - [ ] Ensure sufficient streaming tests
mostly tests
| thought_signature=thought_sig, | ||
| ) | ||
| ) | ||
| elif part["type"] == "reasoning": |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
what is the purpose of implementing both this and _convert_from_v1_to_generativelanguage_v1beta?
afaik this code is never engaged because _convert_from_v1_to_generativelanguage_v1beta filters out of content.
https://docs.langchain.com/oss/python/releases/langchain-v1
https://googleapis.dev/python/generativelanguage/latest/
CHANGELOG
BigQueryVectorSearchembed_image()embbedingspropertyembbedingsparameterTODO
convert_system_message_to_human(langchain_google_genai/chat_models.py:2303)