agent-search-core 0.1.9

In-process SDK runtime for agent-search with optional callback-driven Langfuse tracing

agent-search core SDK

In-process Python SDK for agent-search. This package lets you call the runtime directly inside your own app.

The SDK always requires both:

• A chat model (e.g. langchain_openai.ChatOpenAI)
• A vector store that implements similarity_search(query, k, filter=None)

It does not auto-build these dependencies for you.

Install (PyPI)

python3.11 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip
pip install agent-search-core
python -c "import agent_search; print(agent_search.__file__)"

Quick start

from langchain_openai import ChatOpenAI
from langfuse.langchain import CallbackHandler
from agent_search import advanced_rag
from agent_search.vectorstore.langchain_adapter import LangChainVectorStoreAdapter

vector_store = LangChainVectorStoreAdapter(your_langchain_vector_store)
model = ChatOpenAI(model="gpt-4.1-mini", temperature=0.0)
langfuse_callback = CallbackHandler(
    public_key="...",
    secret_key="...",
    host="https://cloud.langfuse.com",
)

response = advanced_rag(
    "What is pgvector?",
    vector_store=vector_store,
    model=model,
    langfuse_callback=langfuse_callback,
)
print(response.output)

Requirements

• Python >=3.11,<3.14
• A compatible vector store and chat model as shown above.

Build

cd sdk/core
python -m build

Runtime API surface

Primary functions exposed by agent_search:

• advanced_rag
• build_langfuse_callback
• run
• run_async
• get_run_status
• cancel_run

run(...) remains available as a compatibility alias and delegates to advanced_rag(...).

Tracing behavior for advanced_rag(...):

• If you pass langfuse_callback=..., SDK uses that callback for run tracing.
• If langfuse_callback is omitted, SDK does not trace the run.
• langfuse_settings is deprecated and ignored by advanced_rag(...); pass an explicit callback instead.

advanced_rag(...) output schema:

RuntimeAgentRunResponse(
  main_question: str,
  sub_qa: list[SubQuestionAnswer],
  output: str,
  final_citations: list[CitationSourceRow],
)

Config and errors exposed by agent_search:

• RuntimeConfig, RuntimeTimeoutConfig, RuntimeRetrievalConfig, RuntimeRerankConfig
• SDKError, SDKConfigurationError, SDKRetrievalError, SDKModelError, SDKTimeoutError

Vector store compatibility

Runtime SDK expects similarity_search(query, k, filter=None). For LangChain-backed stores, use:

• agent_search.vectorstore.langchain_adapter.LangChainVectorStoreAdapter

Notes

• For the full app (API, DB, UI), run this repo with Docker Compose.
• For SDK-only use, install from PyPI and supply your own model + vector store.

Release guidance

Use the repository release script from project root:

./scripts/release_sdk.sh

The release script verifies the built wheel includes the agent_search package before upload.

Publish flow (requires TWINE_API_TOKEN):

PUBLISH=1 TWINE_API_TOKEN=*** ./scripts/release_sdk.sh

Tag format used by CI release workflow:

• agent-search-core-v<version>