LlamaIndex

Overview

The llama-index-tools-nimble package brings Nimble web search to LlamaIndex. It provides a single tool spec, NimbleToolSpec, that lets LlamaIndex agents and workflows retrieve current information from the web. Search results return as LlamaIndex Document objects. Each document carries the page title and source URL, so answers stay citable and ready for RAG pipelines.

Key Features

Real-time web search — one method, search(), returns fresh results from across the web
Citable output — every Document includes the title and source URL in its metadata
Agent-ready — to_tool_list() plugs directly into any LlamaIndex agent or workflow
RAG-friendly — Document output drops straight into LlamaIndex indexes and query engines

Quick Start

Installation

pip install llama-index-tools-nimble

Setup

Get your API key from Nimble’s dashboard (free trial available). Set it as an environment variable:

export NIMBLE_API_KEY="your-api-key"

Or pass it directly when constructing the tool spec:

from llama_index.tools.nimble import NimbleToolSpec

tool_spec = NimbleToolSpec(api_key="your-api-key")

Direct Search

Call search() on the tool spec to get results back as Document objects. Use max_results to cap how many results come back (default is 6):

from llama_index.tools.nimble import NimbleToolSpec

tool_spec = NimbleToolSpec()
documents = tool_spec.search(
    "latest developments in web data infrastructure",
    max_results=5,
)

for doc in documents:
    print(doc.metadata["title"], "-", doc.metadata["url"])

The loop above prints the title and source URL for each result:

Web Data Infrastructure for AI - https://nimbleway.com/...
The State of Web Data in 2026 - https://example.com/...

Build an AI Agent

Pass the tool spec to a LlamaIndex FunctionAgent with to_tool_list(). The agent can then search the web to answer questions with current facts:

import asyncio
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
from llama_index.tools.nimble import NimbleToolSpec

agent = FunctionAgent(
    tools=NimbleToolSpec().to_tool_list(),
    llm=OpenAI(model="gpt-4o-mini"),
    system_prompt="You are a research assistant. Use web search to answer with current facts.",
)

async def main():
    response = await agent.run("What has Nimble announced recently?")
    print(response)

asyncio.run(main())

Citable Document Output

Every result is a LlamaIndex Document. The title and source URL are embedded in the document text, so the agent can read and cite the source even though it never sees metadata. Each document’s text has this shape:

<title>
URL: <source url>

<page content or snippet>

The title and URL are also available as metadata fields for programmatic use:

Field	Description
`metadata["title"]`	The page title
`metadata["url"]`	The source URL

Use these fields to build citations or deduplicate sources:

from llama_index.tools.nimble import NimbleToolSpec

documents = NimbleToolSpec().search("state of retrieval-augmented generation")

for doc in documents:
    print(f"Source: {doc.metadata['title']} ({doc.metadata['url']})")

Use Results in a LlamaIndex Index

Because search() returns Document objects, results drop straight into a LlamaIndex index for retrieval-augmented generation:

from llama_index.core import VectorStoreIndex
from llama_index.tools.nimble import NimbleToolSpec

# Fetch live web results as Documents
documents = NimbleToolSpec().search(
    "web data infrastructure trends",
    max_results=10,
)

# Index them, then query with citable sources
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("Summarize the key trends.")
print(response)

Agent Skills

MCP Server

Partnerships

Connectors

Proxy

Overview

Key Features

Quick Start

Installation

Setup

Direct Search

Build an AI Agent

Citable Document Output

Use Results in a LlamaIndex Index

Additional Resources

​Overview

​Key Features

​Quick Start

​Installation

​Setup

​Direct Search

​Build an AI Agent

​Citable Document Output

​Use Results in a LlamaIndex Index

​Additional Resources

Overview

Key Features

Quick Start

Installation

Setup

Direct Search

Build an AI Agent

Citable Document Output

Use Results in a LlamaIndex Index

Additional Resources