openai

func ExtractToolParts ¶

func ExtractToolParts(msg *ChatMessage) ([]llms.ContentPart, []llms.ToolCall, []llms.ToolCallResponse)

ExtractToolParts extracts the tool parts from a message.

func MapError ¶

func MapError(err error) error

MapError maps OpenAI-specific errors to standardized error codes.

func WithExtraBody ¶

func WithExtraBody(extraBody map[string]any) llms.CallOption

WithExtraBody allows passing additional fields in the request body that will be sent to the OpenAI-compatible API. These fields will override any existing fields with the same name, allowing you to use provider-specific parameters not directly supported by the library.

Example usage:

llm.GenerateContent(ctx, messages,
    openai.WithExtraBody(map[string]any{
        "enable_thinking": false,
        "chat_template_kwargs": map[string]any{
            "enable_thinking": false,
        },
    }),
)

func WithLegacyMaxTokensField ¶

func WithLegacyMaxTokensField() llms.CallOption

WithLegacyMaxTokensField forces the use of the max_tokens field instead of max_completion_tokens. This is useful when connecting to older OpenAI-compatible inference servers that only support the max_tokens field and don't recognize max_completion_tokens.

Usage:

llm.GenerateContent(ctx, messages,
    llms.WithMaxTokens(100),
    openai.WithLegacyMaxTokensField(), // Forces use of max_tokens field
)

func WithMaxCompletionTokens ¶

func WithMaxCompletionTokens(maxTokens int) llms.CallOption

WithMaxCompletionTokens sets the max_completion_tokens field for token generation. This is the recommended way to limit tokens with OpenAI models.

Usage:

llm.GenerateContent(ctx, messages,
    openai.WithMaxCompletionTokens(100),
)

Note: While llms.WithMaxTokens() still works for backward compatibility, WithMaxCompletionTokens is preferred for clarity when using OpenAI.