modelscope / modelscope/ms-agent

[tool] Add Webz.io News Search provider

Open
#990 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.4k
Forks
521
Avg merge
1d
Merged PRs (30d)
36

Description

Description

Add Webz.io News Search as a modular search tool and deep-research searcher profile.

MS-Agent already has a Tavily search implementation under ms_agent/tools/search and a corresponding deep-research YAML profile. Webz.io would add a news-specific provider for current-events research, company research, risk analysis, and news-grounded agents.

Suggested implementation:

  • Add a webz search package alongside tavily.
  • Configure authentication through WEBZ_API_KEY.
  • Accept a natural-language query and optional filters for publication date, country, language, category, and sentiment.
  • Normalize article titles, URLs, publication dates, source metadata, and relevant excerpts into the existing search interface.
  • Add a searcher.webz.yaml deep-research profile, documentation, and tests.

API documentation: https://docs.webz.io/docs/webz/news-search-api

Webz.io searches recent global news rather than the general web, so it would complement the existing Tavily integration.

Disclosure: I am with Webz.io and would be happy to help with API details or implementation guidance.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the existing Tavily implementation under ms_agent/tools/search and its corresponding deep-research YAML profile to understand the search interface and profile layout. Add the Webz provider with WEBZ_API_KEY authentication, the listed filters and normalized article fields, then add searcher.webz.yaml, documentation, and tests. Done means the provider and profile integrate with the existing search flow and the tests pass.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
search, tooling
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.