Skip to main content

In-process SDK runtime for agent-search

Project description

agent-search core SDK workspace

This workspace contains packaging metadata for the distributable in-process agent_search SDK boundary.

Scope

  • Separates SDK packaging from backend application packaging.
  • Excludes backend-only web and DB dependencies.
  • Produces standalone wheel/sdist artifacts.

Build

cd sdk/core
python -m build

Runtime API surface

Primary functions exposed by agent_search:

  • run
  • run_async
  • get_run_status
  • cancel_run

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

Release guidance

Use the repository release script from project root:

./scripts/release_sdk.sh

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>

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agent_search_core-0.1.0.tar.gz (70.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_search_core-0.1.0-py3-none-any.whl (94.6 kB view details)

Uploaded Python 3

File details

Details for the file agent_search_core-0.1.0.tar.gz.

File metadata

  • Download URL: agent_search_core-0.1.0.tar.gz
  • Upload date:
  • Size: 70.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for agent_search_core-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a4bd7362997000a83523bf5cb8103014f35a9d0426b597df46594175ae719f7f
MD5 553d38009a6de43104a6bc5732684286
BLAKE2b-256 f0ee8eb769fe3a69f5b2b65ed2851ea06acb59ccdf2aea8503046355231ea917

See more details on using hashes here.

File details

Details for the file agent_search_core-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for agent_search_core-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3ae5af9a6f5e3f5a9eb38470c135eb3e2cbd9d81a2005908149f646de8412d85
MD5 3921f24c466073b5106b3d3daa16e1f6
BLAKE2b-256 6d9200c90dad29f4cc6013a56bfe86b443a67a5c1c4d07ecd9c15e170aa63901

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page