langchain-ai/langchain-google

How to use web search tools with ChatAnthropicVertex in Python?

Open

#1,411 opened on Dec 5, 2025

View on GitHub
 (4 comments) (0 reactions) (0 assignees)Python (461 forks)auto 404
anthropic-vertexhelp wantedvertexai

Repository metrics

Stars
 (392 stars)
PR merge metrics
 (PR metrics pending)

Description

Discussed in https://github.com/langchain-ai/langchain-google/discussions/1357

Originally posted by codethestudent November 17, 2025 Hi, I’m trying to use Claude models on Vertex AI through ChatAnthropicVertex in Python, and I’m not sure how tool usage (especially web search tools) is supposed to work.

I couldn’t find any documentation or examples explaining whether:

Tools should be passed directly when constructing the ChatAnthropicVertex model, or

Tools should be attached using BaseChatModel.bind_tools() after creating the model.

I’ve tried both approaches, but tool-calling doesn’t seem to work properly, and I can’t find clear guidance in the docs. (the only docs about web search I found are ChatAnthropic(), ChatVertexAI())

Is ChatAnthropicVertex supposed to support tool-calling (like web search tools)? If so, what is the correct way to attach tools for Claude models running on Vertex?

Any official docs, examples, or guidance would be really appreciated. Thanks

Contributor guide

Research direction
Check if ChatAnthropicVertex supports tool calling by examining the source code or existing tests. Try using BaseChatModel.bind tools() with structured tools and verify the model's response. If tools are not supported, consider raising a feature request.
Tech stack
python
Domain
backendapi
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
1
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonLangChain
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60