Nia Toolkit 集成

使用 LangChain Python 集成 the Nia search and index API。

Nia is a search and index API that continuously provides context from docs, research papers, datasets, codebases, and more—so agents never rely on stale data. Scalable, 5x cheaper, and reliable.

概述

集成详情

Class	Package	Serializable	JS support	Version
NiaToolkit	langchain-nia	❌	❌

Tool features

Returns artifact	Native async	Toolkit	Number of tools	定价
❌	✅	✅	20	Free tier available

设置

The integration lives in the langchain-nia package.

pip

pip install -U langchain-nia

凭证

Sign up at trynia.ai to get an API key.

import getpass
import os

if not os.environ.get("NIA_API_KEY"):
    os.environ["NIA_API_KEY"] = getpass.getpass("Nia API key:\n")

It’s also helpful (but not needed) to set up LangSmith for best-in-class observability/tracing of your tool calls. To enable automated tracing, set your LangSmith API key:

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

Instantiation

Using the toolkit

The NiaToolkit provides all 20 Nia tools with a shared API wrapper. Use include_* flags to control which tool groups are available:

from langchain_nia import NiaToolkit

toolkit = NiaToolkit(
    include_search=True,        # NiaSearch, NiaWebSearch, NiaDeepResearch, NiaUniversalSearch, NiaAdvisor
    include_sources=True,       # NiaIndex, NiaSourceList, NiaSourceSubscribe, NiaSourceSync, NiaRead, NiaGrep, NiaExplore
    include_github=True,        # NiaGitHubSearch, NiaGitHubRead, NiaGitHubGlob, NiaGitHubTree
    include_contexts=True,      # NiaContextSave, NiaContextSearch
    include_dependencies=True,  # NiaDependencySubscribe, NiaDependencyAnalyze
)
tools = toolkit.get_tools()

Using individual tools

You can also use tools directly:

from langchain_nia import NiaSearch

tool = NiaSearch()

Invocation

搜索 across indexed sources

from langchain_nia import NiaSearch

tool = NiaSearch()
tool.invoke({"query": "how to use React hooks"})

搜索 the web

from langchain_nia import NiaWebSearch

tool = NiaWebSearch()
tool.invoke({"query": "latest Python release", "num_results": 5})

Read files from indexed sources

from langchain_nia import NiaRead

tool = NiaRead()
tool.invoke({"source_id": "your-source-id", "path": "README.md"})

Within an agent

from langchain_nia import NiaToolkit

toolkit = NiaToolkit(include_search=True, include_sources=False, include_github=False, include_contexts=False, include_dependencies=False)
tools = toolkit.get_tools()

# pip install -qU "langchain[anthropic]"
from langchain.agents import create_agent

agent = create_agent(
    model="claude-sonnet-4-6",
    tools=tools,
)

agent.invoke(
    {"messages": [{"role": "user", "content": "Search for React hooks best practices"}]}
)

Available tools

搜索 tools

• NiaSearch - Semantic search across indexed repos, docs, datasets, and more
• NiaWebSearch - Web search with category filtering and date range
• NiaDeepResearch - Multi-step comprehensive research
• NiaUniversalSearch - Search all sources simultaneously
• NiaAdvisor - Analyze code against indexed documentation

Source management tools

• NiaIndex - Index new sources (repos, docs, papers, datasets)
• NiaSourceList - List indexed sources with filtering
• NiaSourceSubscribe - Subscribe to pre-indexed public sources
• NiaSourceSync - Re-sync sources to pull latest changes
• NiaRead - Read files/pages from indexed sources
• NiaGrep - Regex search within indexed sources
• NiaExplore - Browse file tree of indexed sources

GitHub tools

• NiaGitHubSearch - Search code in GitHub repositories
• NiaGitHubRead - Read files from GitHub repos
• NiaGitHubGlob - Find files matching glob patterns
• NiaGitHubTree - Browse repo file tree structure

Context and memory tools

• NiaContextSave - Save context for cross-agent sharing
• NiaContextSearch - Semantic search over saved contexts

Dependency tools

• NiaDependencySubscribe - Auto-subscribe to docs for project dependencies
• NiaDependencyAnalyze - Preview what would be indexed from a manifest

API 参考

所有 Nia tools and configurations, see the langchain-nia GitHub repository.

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.