Create

API Reference

Chat

Completions

Create

chat.completions.create(CompletionCreateParams**kwargs) -> completion_messageCompletionMessageidstrmetricslistCreateChatCompletionResponse

post/chat/completions

Generate a chat completion for the given messages using the specified model.

Parameters

messagesiterable

Iterable[MessageParam]

List of messages in the conversation.

Hide ParametersShow Parameters

contentunionroleliteralUserMessage

contentunionroleliteralSystemMessage

contentunionroleliteraltool_call_idstrToolResponseMessage

roleliteralcontentContentstop_reasonliteraltool_callslistCompletionMessage

modelstr

The identifier of the model to use.

max_completion_tokensint

optional

The maximum number of tokens to generate.

minimum1

repetition_penaltyfloat

optional

Controls the likelyhood and generating repetitive responses.

minimum1

maximum2

response_formatResponseFormat

optional

An object specifying the format that the model must output. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. If not specified, the default is {"type": "text"}, and model will return a free-form text response.

Hide ParametersShow Parameters

ResponseFormatJsonSchemaResponseFormatclass

Configuration for JSON schema-guided response generation.

Hide ParametersShow Parameters

json_schemanamestrschemaobjectResponseFormatJsonSchemaResponseFormatJsonSchema

The JSON schema the response should conform to.

Hide ParametersShow Parameters

namestr

The name of the response format.

schemaobject

The JSON schema the response should conform to. In a Python SDK, this is often a pydantic model.

typeliteral

Literal["json_schema"]

The type of response format being defined. Always json_schema.

Hide ParametersShow Parameters

"json_schema"

ResponseFormatTextResponseFormatclass

Configuration for text-guided response generation.

Hide ParametersShow Parameters

typeliteral

Literal["text"]

The type of response format being defined. Always text.

Hide ParametersShow Parameters

"text"

streamliteral

optional

Literal[false]

If True, generate an SSE event stream of the response. Defaults to False.

Hide ParametersShow Parameters

false

temperaturefloat

optional

Controls randomness of the response by setting a temperature. Higher value leads to more creative responses. Lower values will make the response more focused and deterministic.

minimum0

maximum1

tool_choiceToolChoiceUnionMember0literalToolChoice

optional

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

none is the default when no tools are present. auto is the default if tools are present.

Hide ParametersShow Parameters

ToolChoiceUnionMember0type

Literal["none", "auto", "required"]

none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools.

Hide ParametersShow Parameters

"none"

"auto"

"required"

ToolChoiceChatCompletionNamedToolChoiceclass

Specifies a tool the model should use. Use to force the model to call a specific function.

Hide ParametersShow Parameters

functionnamestrToolChoiceChatCompletionNamedToolChoiceFunction

Hide ParametersShow Parameters

namestr

The name of the function to call.

typeliteral

Literal["function"]

The type of the tool. Currently, only function is supported.

Hide ParametersShow Parameters

"function"

toolsiterable

optional

functionToolFunctiontypeliteralIterable[Tool]

List of tool definitions available to the model

Hide ParametersShow Parameters

functionnamestrdescriptionstrparametersDict[str, object]strictboolToolFunction

Hide ParametersShow Parameters

namestr

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

descriptionstr

optional

A description of what the function does, used by the model to choose when and how to call the function.

parametersDict[str, object]

optional

Dict[str, object]

The parameters the functions accepts, described as a JSON Schema object. Omitting parameters defines a function with an empty parameter list.

strictbool

optional

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

typeliteral

Literal["function"]

The type of the tool. Currently, only function is supported.

Hide ParametersShow Parameters

"function"

top_kint

optional

Only sample from the top K options for each subsequent token.

minimum0

top_pfloat

optional

Controls diversity of the response by setting a probability threshold when choosing the next token.

minimum0

maximum1

userstr

optional

A unique identifier representing your application end-user for monitoring abuse.

Returns

completion_messageCompletionMessageidstrmetricslistCreateChatCompletionResponse

HTTPTypeScriptPythonGo

from llama_api_client import LlamaAPIClient

client = LlamaAPIClient(
    api_key="My API Key",
)
create_chat_completion_response = client.chat.completions.create(
    messages=[{
        "content": "string",
        "role": "user",
    }],
    model="model",
)
print(create_chat_completion_response.id)

200 Example

{
  "completion_message": {
    "role": "assistant",
    "content": "string",
    "stop_reason": "stop",
    "tool_calls": [
      {
        "id": "id",
        "function": {
          "arguments": "arguments",
          "name": "name"
        }
      }
    ]
  },
  "id": "id",
  "metrics": [
    {
      "metric": "metric",
      "value": 0,
      "unit": "unit"
    }
  ]
}