Skip to content

Add new reasoning effort values to ChatOpenAIResponses #419

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.

Sign up for GitHub

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

Open
xxdavid wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add new reasoning effort values to ChatOpenAIResponses #419

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions lib/chat_models/reasoning_options.ex
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,8 @@ defmodule LangChain.ChatModels.ReasoningOptions do

## Fields

- `effort` - Constrains effort on reasoning. Supported values: :minimal, :low, :medium, :high
- `effort` - Constrains effort on reasoning. Supported values: :none, :minimal, :low, :medium,
:high, :xhigh
- `generate_summary` - (Deprecated) A summary of the reasoning performed. Use `summary` instead.
- `summary` - A summary of the reasoning performed. Supported values: :auto, :concise, :detailed
"""
Expand All @@ -17,7 +18,11 @@ defmodule LangChain.ChatModels.ReasoningOptions do
@primary_key false

embedded_schema do
field(:effort, Ecto.Enum, values: [:minimal, :low, :medium, :high], default: nil)
field(:effort, Ecto.Enum,
values: [:none, :minimal, :low, :medium, :high, :xhigh],
default: nil
)

field(:generate_summary, Ecto.Enum, values: [:auto, :concise, :detailed], default: nil)
field(:summary, Ecto.Enum, values: [:auto, :concise, :detailed], default: nil)
end
Expand Down Expand Up @@ -85,8 +90,10 @@ defmodule LangChain.ChatModels.ReasoningOptions do

@doc """
Returns the list of valid effort values.

Different models allow different reasoning effort values. Consult the OpenAI docs.
"""
def valid_efforts, do: [:minimal, :low, :medium, :high]
def valid_efforts, do: [:none, :minimal, :low, :medium, :high, :xhigh]

@doc """
Returns the list of valid summary values.
Expand Down