only google search?how about baidu search?how to use it?

[henbucuoshanghai]

Checked other resources

• This is a bug, not a usage question.
• I added a clear and descriptive title that summarizes this issue.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
• This is not related to the langchain-community package.
• I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
• I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Example Code

response = genai_client.models.generate_content(
model=configurable.query_generator_model,
contents=formatted_prompt,
config={
"tools": [{"google_search": {}}],
"temperature": 0,
},
I can only use the google saerch? how about others,like www.baidu.com?
I want baidu only,how?tks

Error Message and Stack Trace (if applicable)

No response

Description

response = genai_client.models.generate_content(
model=configurable.query_generator_model,
contents=formatted_prompt,
config={
"tools": [{"google_search": {}}],
"temperature": 0,
},
I can only use the google saerch? how about others,like www.baidu.com?
I want baidu only,how?tks

System Info

response = genai_client.models.generate_content(
model=configurable.query_generator_model,
contents=formatted_prompt,
config={
"tools": [{"google_search": {}}],
"temperature": 0,
},
I can only use the google saerch? how about others,like www.baidu.com?
I want baidu only,how?tks

[starchou6]

Hello, this should not be a bug.

You can create a tool like this:

@tool
def baidu_search(query: str) -> str:
    """Search using Baidu search engine"""
    search_url = f"https://www.baidu.com/s?wd={query}"
    return requests.get(search_url)

Usage

# Bind your custom Baidu search tool
llm_with_tools = llm.bind_tools([baidu_search])

# Use it instead of genai_client
response = llm_with_tools.invoke(formatted_prompt)

[henbucuoshanghai]

kind and useful ansewer,how can i use this in this code? tks bseides the format of output is the same?
response = genai_client.models.generate_content(
model=configurable.query_generator_model,
contents=formatted_prompt,
config={
"tools": [{"google_search": {}}],
"temperature": 0,
},

[starchou6]

kind and useful ansewer,how can i use this in this code? tks bseides the format of output is the same? response = genai_client.models.generate_content( model=configurable.query_generator_model, contents=formatted_prompt, config={ "tools": [{"google_search": {}}], "temperature": 0, },

Here's how to modify your existing code to use the custom Baidu search tool:

from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_core.tools import tool
import requests
from bs4 import BeautifulSoup

# Your custom Baidu search tool
@tool
def baidu_search(query: str) -> str:
    """Search using Baidu search engine"""
    search_url = f"https://www.baidu.com/s?wd={query}"
    response = requests.get(search_url)
    soup = BeautifulSoup(response.content, 'html.parser')
    
    results = []
    for container in soup.find_all('div', class_='result')[:5]:
        title = container.find('h3').get_text()
        url = container.find('h3').find('a').get('href')
        results.append(f"{title}: {url}")
    
    return "\n".join(results)

# Replace your genai_client with LangChain's version
llm = ChatGoogleGenerativeAI(
    model=configurable.query_generator_model,
    temperature=0
)

# Bind your custom Baidu search tool
llm_with_tools = llm.bind_tools([baidu_search])

# Use it (similar to your original code)
response = llm_with_tools.invoke(formatted_prompt)

I think the output format should be the same but still you need debug and confirm it.
The response will still be a structured object with:

• response.content - The main response text
• response.tool_calls - Tool calls made during execution
• Same metadata and structure as your original code

[henbucuoshanghai]

very kind，tks ,I will try it.thank u .