Docs /Templates/ sinapsis-anthropic

AnthropicMultiModal

sinapsis-anthropicAnthropicanthropicchatbotscontextlarge_language_models

Python template · sinapsis_anthropic.templates.anthropic_multimodal

Overview

Template for multimodal Anthropic chat processing.

Capabilities

Capabilities: not set

Installation

Install the published package using pip or uv.

Terminalbash
pip install sinapsis-anthropic==1.0.0
uv pip install sinapsis-anthropic==1.0.0
uv add sinapsis-anthropic==1.0.0

Configuration

Effective fields from the inspector schema, including nested Pydantic model fields.

metadata
sinapsis_core.template_base.base_models.TemplateMetadata | None
Optional
Default: null
init_argsRequired

Anthropic model configuration.

LLMInitArgs
Required
Default: null
llm_model_nameRequired

The name or path of the LLM model to use (e.g., 'claude-3-7-sonnet-latest', 'TheBloke/Llama-2-7B-GGUF').

str
Required
Default: null
web_search

Whether to enable Anthropic's web search tool.

bool
Optional
Default: false
completion_argsRequired

Anthropic generation arguments.

AnthropicCompletionArgs
Required
Default: null
top_k

Top-k sampling parameter.

int | None
Optional
Default: null
top_p

Nucleus sampling parameter.

float | None
Optional
Default: null
max_tokensRequired

Maximum number of tokens to generate.

int
Required
Default: null
temperature

Sampling temperature.

float | None
Optional
Default: null
service_tier

Anthropic service tier.

typing.Literal['auto', 'standard_only']
Optional
Default: "standard_only"
stop_sequences

Custom stop sequences.

list[str] | None
Optional
Default: null
response_format

Provider-neutral structured output config.

LLMResponseFormat
Optional
Default: null
type_

Output mode. Aliased to `type`.

typing.Literal['text', 'json_object']
Optional
Default: "text"
schema_

Optional schema used for structured JSON output. Aliased to `schema`.

SchemaDefinition
Optional
Default: null
required

Required root property names.

list[str]
Optional
Default: null
properties

Root schema properties.

dict[str, str | sinapsis_chatbots_base.helpers.schemas.PropertyDefinition]
Optional
Default: null
additional_properties

Whether extra root-level fields are allowed.

bool | None
Optional
Default: null
cleanup_response
bool
Optional
Default: true
extended_thinking

Extended-thinking configuration.

AnthropicThinkingArgs
Optional
Default: null
type

Whether extended thinking is enabled.

typing.Literal['enabled', 'disabled']
Optional
Default: "disabled"
budget_tokens

Maximum tokens reserved for reasoning blocks.

int
Optional
Default: 2048
reasoning_end_tag
str | None
Optional
Default: "</think>"
reasoning_start_tag
str | None
Optional
Default: "<think>"

Configuration example

Example from the Python docstring:

yaml
agent:
  name: my_test_agent
templates:
- template_name: InputTemplate
  class_name: InputTemplate
  attributes: {}
- template_name: AnthropicMultiModal
  class_name: AnthropicMultiModal
  template_input: LLMConversationInput
  attributes:
    init_args:
      llm_model_name: claude-sonnet-4-6
    completion_args:
      max_tokens: 1024
      temperature: 0.2
      service_tier: standard_only
    extended_thinking:
      type: disabled
    web_search: false
Show schema-based configuration skeleton
yaml
templates:
  - template_name: "AnthropicMultiModal"
    class_name: "AnthropicMultiModal"
    attributes:
      init_args:
        llm_model_name: "<required>"
      web_search: false
      completion_args:
        top_k: null
        top_p: null
        max_tokens: "<required>"
        temperature: null
        service_tier: "standard_only"
        stop_sequences: null
        response_format:
          type_: "text"
          schema_:
            required: null
            properties: null
            additional_properties: null
      cleanup_response: true
      extended_thinking:
        type: "disabled"
        budget_tokens: 2048
      reasoning_end_tag: "</think>"
      reasoning_start_tag: "<think>"

Inheritance

Immediate parent: sinapsis_chatbots_base.templates.llm_multimodal_base.LLMMultimodalTemplateBase

Environment variables

Environment definitions belong to their canonical Python modules.

No directly related environment variables listed.