refactor!: Replace Pydantic model for LLM config with plain dict #658
Conversation
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
edwardzjl
force-pushed
the
llmc
branch
2 times, most recently
from
bace08b to
7554263
Compare
This change replaces the Pydantic model used for the LLM configuration (`llm`) with a plain dictionary, improving flexibility by exposing all parameters directly to the deployer.
While it would be preferable to annotate `llm` as `langchain_openai.ChatOpenAI`, there is a limitation: Pydantic raises an error ("cannot pickle '_thread.RLock' object"), likely due to incompatibility within `langchain_openai.ChatOpenAI`.
Using a plain dictionary removes validation at startup, but the default empty dict is sufficient to create a `ChatOpenAI` instance, making this an acceptable tradeoff for now.
|
I'm wrong. As I have |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Pull Request Checklist
Describe what you have changed in this PR.
This change replaces the Pydantic model used for the LLM configuration (
llm) with a plain dictionary, improving flexibility by exposing all parameters directly to the deployer.While it would be preferable to annotate
llmaslangchain_openai.ChatOpenAI, there is a limitation: Pydantic raises an error ("cannot pickle '_thread.RLock' object"), likely due to incompatibility withinlangchain_openai.ChatOpenAI.Using a plain dictionary removes validation at startup, but the default empty dict is sufficient to create a
ChatOpenAIinstance, making this an acceptable tradeoff for now.