langchain-keenable

This package contains the LangChain integration with Keenable, a web search and page-fetch API built for AI agents.

Installation

pip install -U langchain-keenable

Optionally set a KEENABLE_API_KEY environment variable to use the authenticated endpoints. Without a key, both search and fetch transparently fall back to their keyless public endpoints.

export KEENABLE_API_KEY="your-api-key"  # optional; create one at https://keenable.ai/console

The API endpoint defaults to https://api.keenable.ai and can be overridden (e.g. for staging) with the KEENABLE_API_URL environment variable. It must be an https:// URL.

Tools

KeenableSearch

Queries the Keenable search API and returns a list of result dictionaries. All filters are per-invocation, so an agent can vary them per query:

from langchain_keenable import KeenableSearch

# Works with no key (keyless public endpoint) or with KEENABLE_API_KEY set.
tool = KeenableSearch()

results = tool.invoke({
    "query": "typescript best practices",
    "site": "github.com",          # optional: restrict to a domain
    "published_after": "2026-01-01",  # optional: YYYY-MM-DD date filters
    # "published_before" / "acquired_after" / "acquired_before" also supported
})
for result in results:
    print(result["title"], result["url"])

mode defaults to "pro" (deeper retrieval). It can be set as a class default and overridden per call.

KeenableFetch

Fetches a page via Keenable and returns its main content as markdown — pair it with KeenableSearch so an agent can read the pages it discovers:

from langchain_keenable import KeenableFetch

tool = KeenableFetch()
page = tool.invoke({"url": "https://example.com/article"})
print(page["title"], page["content"])

Error handling

Both tools set handle_tool_error = True: rate limits (429), auth (401) and credit (402) errors, network timeouts and malformed responses are surfaced to the agent as an error string (carrying the backend's message) rather than raising and crashing the agent loop.

Async

Both tools implement _arun, so await tool.ainvoke({...}) works (the request runs in a worker thread).

The tools can be bound to any LangChain chat model that supports tool calling and used within an agent.

Project links

Data verified by PyPI on
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for ilya.bogin from gravatar.com ilya.bogin

Credits

Author: Keenable

GitHub Statistics

Data verified by PyPI on 
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT License (MIT)

Requires

Python <4.0, >=3.10

Classifiers

Report project as malware

Download files

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

Source Distribution

langchain_keenable-0.1.2.tar.gz (145.7 kB view details)

Uploaded Source

Built Distribution

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

langchain_keenable-0.1.2-py3-none-any.whl (9.7 kB view details)

Uploaded Python 3

File details

Details for the file langchain_keenable-0.1.2.tar.gz.

File metadata

  • Download URL: langchain_keenable-0.1.2.tar.gz
  • Upload date:
  • Size: 145.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for langchain_keenable-0.1.2.tar.gz
Algorithm Hash digest
SHA256 be9578b9623df6258c7be3f1d6946da568d9e872125be9c1c8716e402a78fb07
MD5 88d33806ecf6073af9a896e8e65ac84c
BLAKE2b-256 91926886c3ba0177aa0cf37e2061dbf40c7011ca3a1b6cb302ff87d46c6aa899

See more details on using hashes here.

Provenance

The following attestation bundles were made for langchain_keenable-0.1.2.tar.gz:

Publisher: publish.yml on keenableai/langchain-keenable

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file langchain_keenable-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_keenable-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 1b2e79f379dfe96627cd47635fdc581a40433b51483b0ef09f2629f605fd0c51
MD5 d3135156b3d40da8209a70f88e0a5371
BLAKE2b-256 c33ab47985db882bd60416a1b89ae413d619c4dde5814ce24c9afeed031503c0

See more details on using hashes here.

Provenance

The following attestation bundles were made for langchain_keenable-0.1.2-py3-none-any.whl:

Publisher: publish.yml on keenableai/langchain-keenable

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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