assistant-service-kit 0.1.0

Reusable kit for building LangChain-based assistant services with auth, tenancy, tools, RAG, tracing, and observability.

Assistant Service Kit

Reusable Python package for building LangChain-based assistant services with FastAPI, auth, tenancy, tools, RAG, tracing, storage, and observability.

Install

Base runtime:

pip install assistant-service-kit

Provider-specific installs:

pip install "assistant-service-kit[rag,gemini]"
pip install "assistant-service-kit[rag,openai]"
pip install "assistant-service-kit[rag,anthropic]"

For local development from this package directory:

pip install -e ".[dev]"

Core Pieces

• AssistantDefinition: declares the assistant server contract.
• AssistantEndpoints / EndpointPolicy: declares enabled routes, custom paths, names, and endpoint permissions.
• AuthConnector: supports no-auth, user-only, gateway token, API key, and custom identity resolution.
• LLMProviderRegistry: Gemini, OpenAI, Anthropic, and fake chat model providers.
• EmbeddingProviderRegistry: Gemini, OpenAI, Anthropic, and fake embedding providers.
• ToolRegistry / ToolPolicy: exposes and validates tools by tenant, user, roles, and limits.
• SQLAlchemyTraceStore / InMemoryTraceStore: reusable chat trace persistence.
• PostgresRagStore / VectorStoreConnector: reusable RAG storage and vector-store integration points.
• answer_with_langchain_agent: LangChain tool-calling orchestrator with observability metadata.

Minimal Example

from assistant_service_kit import (
    AssistantDefinition,
    AssistantEndpoints,
    ConfiguredLLMConnector,
    InMemoryTraceStore,
    LLMRuntimeConfig,
    NoAuthConnector,
    TenancyMode,
    ToolRegistry,
    create_assistant_server,
)

definition = AssistantDefinition(
    name="demo",
    title="Demo Assistant",
    base_path="/api/assistant",
    tenancy_mode=TenancyMode.NONE,
    system_prompt="Answer clearly.",
    tool_registry=ToolRegistry([]),
    llm=ConfiguredLLMConnector(
        config_factory=lambda: LLMRuntimeConfig(provider="fake", model="fake", extra={"response": "ok"})
    ),
    create_schema=lambda: None,
    get_db=lambda: None,
    trace=InMemoryTraceStore(),
    auth=NoAuthConnector(),
    endpoints=AssistantEndpoints(chat=False, conversations=False, messages=False, feedback=False),
)

app = create_assistant_server(definition)

Status

The package is in alpha. APIs can change until the first stable release.