Add Support for Gemini Models – Leverage Larger Context Windows and Cost Benefits #475
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Outdated suggestions cannot be applied.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.
Description:
Overview:
This PR introduces support for Gemini models, which offer larger context windows and reduced costs. These benefits enable developers to provide more detailed instructions (prompts) to guide the agents, enhancing overall performance.
Changes Made:
New GeminiConfig:
GeminiConfig
class incamel/config.py
that removes the unsupportedlogit_bias
argument. This change addresses the ticket regarding Gemini models’ incompatibility withlogit_bias
.Updated Files:
camel/agents/chat_agent.py
camel/configs.py
camel/model_backend.py
camel/typing.py
camel/utils.py
run.py
Rationale:
Gemini models are chosen for their ability to handle larger context windows, allowing more extensive and precise prompt instructions. Their lower cost also makes them an attractive option, facilitating better guidance for agents without increasing expenses.