Skip to content

[Feature]: Add OPEN_AI_LLM_TIMEOUT environment variable #1010

@joseluisll

Description

@joseluisll

Problem or Use Case

When using local LLM providers such as OLLAMA or LM Studio, having a hardcoded limit of 900 seconds is not enough. This defeats the purpose of the local provider, and force us to use small models that have very limited capabilities. Currently, the timeout field for the OPENAI provider is hardcoded to 900 seconds. Add an OPEN_AI_LLM_TIMEOUT environment variable, to set the timeout field for each LLM call.

Proposed Solution

Add an OPEN_AI_LLM_TIMEOUT , in seconds. This is consistent to the other variables such as URL, KEY, model ID.

Alternatives Considered

Add a configuration in the config.yaml

Feature Type

Configuration option

Scope

Small (single file, < 50 lines)

Contribution

  • I'd like to implement this myself and submit a PR

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions