Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Unique Web Search

Configurable web search tool for Unique assistants: search the web, read pages, and return citation-ready content chunks.

Search Proxy (recommended)

Outbound web access should go through Unique Search Proxy (connectors/unique_search_proxy/). When SEARCH_PROXY_BASE_URL is set, search and crawl calls use unique-search-proxy-sdk; credentials and provider egress stay on the proxy pod.

Mode When Behaviour
Proxy (recommended) SEARCH_PROXY_BASE_URL set _proxy_search / _proxy_crawl via the SDK
Legacy URL unset Direct provider calls from this process (_legacy_search / _legacy_crawl)
  • New standard engines (Brave, Perplexity) are proxy-only — legacy raises.
  • Custom API always runs locally (never routed through the proxy).
  • Future provider work targets Search Proxy only; legacy is preserved for migrated engines.

Packages involved: unique-search-proxy-core (schemas), unique-search-proxy-sdk (HTTP), unique-search-proxy (server). System overview: connectors/unique_search_proxy/README.md.

Architecture

Web Search Tool Architecture

Search engine kinds

Standard search

Query → normalised results (URL / title / snippet / optional content). Optional page crawl via the configured crawler.

Engine Proxy Notes
Google legacy + proxy Requires scraping by default
Brave proxy-only Rich snippets; ExposableParam knobs
Perplexity proxy-only Content extraction knobs; ExposableParam
Custom API always local Your REST endpoint

Standard engines that live in proxy-core use ExposableParam (expose + value) for optional provider knobs. See Search Engines README.

Agent search (grounding)

An upstream AI agent / grounded model searches and returns opaque text that this tool parses into WebSearchResults.

Engine Proxy Notes
Bing (Azure AI Foundry grounding) legacy + proxy Configurable requires_scraping
VertexAI (Gemini grounding) legacy + proxy Configurable requires_scraping

Agent engines do not use ExposableParam.

Web crawlers (page readers)

Crawler Auth Notes
Basic none HTTP + content-type toggles; tool-local url_blocked_patterns (legacy)
Tavily TAVILY_API_KEY Extract API
Jina JINA_API_KEY Reader API
Firecrawl FIRECRAWL_API_KEY Batch scrape

No Crawl4AI. Crawler configs have no exposable LLM knobs.

Execution modes

Mode Status Behaviour
V1 Stable Refine query → search → crawl → process
V2 Stable Parallel plan steps (search / read URL)
V3 Experimental Agent loop: snippet search vs on-demand read_urls

Proxy vs legacy is transparent to executors.

Detailed subsystem docs

Configuration

  • SEARCH_PROXY_BASE_URL — enables the Search Proxy client
  • Provider API keys (on the proxy pod when proxy is enabled; otherwise on assistants-core for legacy)
  • Search / crawler / content-processing settings via WebSearchConfig

Dependency management (uv.lock + min/latest testing)

This package is a library and uses uv for dependency management.

We run tests additionally with minimal dependencies to ensure that the listed ranges are valid. NOTE: We use lowest-direct, not lowest. Lowest attempts to use the lowest possible dependency versions transitively causing issues if a dependency has incorrect metadata. Example:

  • google-cloud-aiplatform says it works with shapely<3.0.0.
  • The lowest resolver assumes 1.0 which needs python 2 -> breaks Therefore we use lowest-direct which only sets our direct dependencies to lowest. However, this only correctly verifies our min dependencies if our code correctly lists all the required dependencies and never imports a transitive dependency. We therefore use deptry to ensure we don't use transitive dependencies and that we have no unused dependencies.

Test locally

  • Latest deps and deptry:
cd tool_packages/unique_web_search
uv sync
uv run pytest
uv run deptry
  • Min deps:
cd tool_packages/unique_web_search
uv venv
uv pip install -e . --resolution=lowest-direct
uv export --only-group dev --no-hashes | uv pip install -r -
uv run --no-sync pytest

Download files

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

Source Distribution

unique_web_search-2026.34.0.dev7.tar.gz (114.4 kB view details)

Uploaded Source

Built Distribution

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

unique_web_search-2026.34.0.dev7-py3-none-any.whl (174.1 kB view details)

Uploaded Python 3

File details

Details for the file unique_web_search-2026.34.0.dev7.tar.gz.

File metadata

  • Download URL: unique_web_search-2026.34.0.dev7.tar.gz
  • Upload date:
  • Size: 114.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for unique_web_search-2026.34.0.dev7.tar.gz
Algorithm Hash digest
SHA256 0baf767251aeb55dcc232f3d11b4dc461f4edb12d1939f514452a4506dc73f00
MD5 a849679b08d45529ea9ca50deb1ee940
BLAKE2b-256 34cfb26aeb87faa6ac1cc95746a892760a7f753be038ca81e02cd230ed16bf53

See more details on using hashes here.

File details

Details for the file unique_web_search-2026.34.0.dev7-py3-none-any.whl.

File metadata

  • Download URL: unique_web_search-2026.34.0.dev7-py3-none-any.whl
  • Upload date:
  • Size: 174.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for unique_web_search-2026.34.0.dev7-py3-none-any.whl
Algorithm Hash digest
SHA256 1d457d1e30fd7705688bc235836ddeed555e35949b00158e01661591dd51bfa6
MD5 bc410fd047555c885278783983d00a1c
BLAKE2b-256 ab584adc108bd35dff69a5b15e0e2e5717a20c437af0154e01a0128f1c8961be

See more details on using hashes here.

Release history Release notifications | RSS feed

Supported by

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