Skip to main content

AgentWebSearch Package

CI CD

Description

...

Quickstart

Create a AgentWebSearch Object

from agentwebsearch import AgentWebSearch
from agentwebsearch.websearch.request import WebSearchRequest
from agentwebsearch.search.client import DefaultSearchClient
from agentwebsearch.webscraper import DefaultWebScraper
from agentwebsearch.indexsearch import HNSWInMemoryIndexDB
from agentwebsearch.llm import OpenAIChatModel
from agentwebsearch.embedding import OpenAIEmbeddingModel


embedding_model = OpenAIEmbeddingModel(
    model="text-embedding-3-large",
    api_key="YOUR_OPENAI_API_KEY"
)

llm = OpenAIChatModel(
    model="gpt-4o",
    api_key="YOUR_OPENAI_API_KEY",
    temperature=0.7
)

index_db = HNSWInMemoryIndexDB(embedding_model=embedding_model)
search_client = DefaultSearchClient()
scraper = DefaultWebScraper()

websearch = AgentWebSearch(
    search_client=search_client,
    index_db=index_db,
    scraper=scraper,
    llm=llm,
    embedding_model=embedding_model
)

Execute AgentWebSearch

from agentwebsearch.websearch.request import RequestQuery, RequestQueryMessage

req = WebSearchRequest(
    query=RequestQuery(
        messages=[
            RequestQueryMessage(
                role="user",
                content="Wann wurde der Bundeskanzler 2025 gewählt?"
            )
        ]
    )
)

result = websearch.execute(req)
# or
for result in websearch.execute(req, stream=True):
    print(result)
    yield result

Deploy as MCP-Server

# server.py
from agentwebsearch.mcp import WebSearchFastMCP

mcp = WebSearchFastMCP("Demo 🚀")


@mcp.tool
def other_tool():
    return "Other tool"


if __name__ == "__main__":
    # available tools:
    #   - websearch
    #   - other_tool

    mcp.run(
        transport="streamable-http",
        host="127.0.0.1",
        port=8000,
        path="/mcp"
    )

# python run server.py

Metadata

Release files for agentwebsearch-py 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agentwebsearch-py 0.2.0
File Size Uploaded Provenance Actions
agentwebsearch_py-0.2.0.tar.gz 112.3 kB With provenance Details for agentwebsearch_py-0.2.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agentwebsearch-py 0.2.0
File Interpreter ABI Platform Actions
agentwebsearch_py-0.2.0-py3-none-any.whl Python 3 none any Details for agentwebsearch_py-0.2.0-py3-none-any.whl

Total release size: 135.6 kB

Release files / agentwebsearch_py-0.2.0.tar.gz

Download URL agentwebsearch_py-0.2.0.tar.gz
Size 112.3 kB
Tags Source
SHA-256 checksum
How to use checksums
4741c5c553e56659582d804331656f08e27b7b878a92c8ca6e063c839c671d35
BLAKE2b-256 checksum
How to use checksums
85bfbe0ce3d87554ed6b8e64e4270f9c70f711b928171001d31c45f7b5e6f1c6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 25, 2025.

Transparency log

Release files / agentwebsearch_py-0.2.0-py3-none-any.whl

Download URL agentwebsearch_py-0.2.0-py3-none-any.whl
Size 23.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
037a5e1512a7d62560cddbdf4c98ad3422aba291a93ce31cb8e43eae36e5c531
BLAKE2b-256 checksum
How to use checksums
a8b7c49b6333a190e1e51d262a96d4daf4e78c31059f581bf3928c1625268dd3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 25, 2025.

Transparency log

Security for agentwebsearch-py 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for agentwebsearch_py-0.2.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 25, 2025.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page