For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Contact usJoin the Discord
ManualAPI GuideAPI Reference
  • Getting started
    • Introduction
    • Quickstart
    • How it works
  • Installation Options
    • Package Install
    • Docker
    • Development
  • Configuration
    • CLI
    • Settings & Profiles
    • Model Configuration
  • Inference Providers
    • Overview
    • Ollama
    • LM Studio
    • LlamaCPP Server
    • vLLM
  • Integrations
    • Overview
    • Claude Code
    • Claude Desktop
    • Claude for Microsoft 365
    • OpenCode
  • Built-in Tools
    • Web Tools
    • Database Tools
  • Storage Providers
    • Vector Store
    • Object Storage
  • User Interface
    • Workbench
  • Observability
    • Observability
  • Reference
    • Troubleshooting
LogoLogo
Contact usJoin the Discord
On this page
  • Supported web tools
  • How to install
  • Settings reference
  • Enable web fetch
  • Enable web search
  • Settings
Built-in Tools

Web Tools

Was this page helpful?
Previous

Database Tools

Next
Built with

This page covers the server-side configuration for built-in web tools.

Use this together with Tools for request examples.

Supported web tools

Built-in web tools include:

  • web_search_v1
  • web_fetch_v1
  • /v1/tools/web-search
  • /v1/tools/web-fetch

web_extract_v1 remains accepted as a legacy alias for web_fetch_v1.

How to install

Install requirements:

  • private-gpt[tool-web-scraping]
  • or private-gpt[tools]
  • or private-gpt[core]

After installing or updating Playwright, download the required browsers:

$playwright install

Settings reference

Enable web fetch

web_fetch_v1 and /v1/tools/web-fetch require web_fetch.enabled: true.

1web_fetch:
2  enabled: true
3  timeout_seconds: 15

Enable web search

web_search_v1 and /v1/tools/web-search require both web fetch and web search, plus a configured provider.

1web_fetch:
2  enabled: true
3
4web_search:
5  enabled: true
6  provider: brave
7  processor: best_links
8  num_links: 20
9  mode_quality: fast
10  cached: false
11  context_token: 0
12
13brave:
14  api_key: ${PGPT_BRAVE_API_KEY:}
15  rate_limit: 1

web_search depends on web fetching, so web_fetch.enabled must also be true.

Settings

SettingDescription
web_fetch.enabledEnables URL fetching and text extraction.
web_fetch.timeout_secondsTimeout for fetching a page.
web_search.enabledEnables web search.
web_search.providerSearch provider. Current built-in options are brave and mock.
web_search.processorPost-processing strategy for results.
web_search.num_linksMaximum number of fetched search results.
web_search.mode_qualityPreset that controls the fast vs accurate parameter block.
web_search.cachedEnables caching for repeated searches.
web_search.context_tokenOptional token budget used by the result processor. 0 disables the limit.
brave.api_keyBrave Search API key. Required when using provider: brave.
brave.rate_limitMinimum seconds between Brave API requests.