zilliztech/deep-searcher — 8.0k Stars

zilliztech

deep-searcher

Python

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Last updated Aug 8, 2026

8.0k

Stars

771

Forks

Issues

Stars/day

Attention Score

View on GitHub ↗ Open in github.dev

Topics

#agent #agentic-rag #claude #deep-research #deepseek #deepseek-r1 #grok #grok3 #llama4 #llm #milvus #openai #qwen3 #rag #reasoning-models #vector-database #zilliz

Language breakdown

Python 99.9%

Dockerfile 0.1%

Makefile 0.0%

▸ Files click to expand

README

DeepSearcher combines cutting-edge LLMs (OpenAI o3, Qwen3, DeepSeek, Grok 4, Claude 4 Sonnet, Llama 4, QwQ, etc.) and Vector Databases (Milvus, Zilliz Cloud etc.) to perform search, evaluation, and reasoning based on private data, providing highly accurate answer and comprehensive report. This project is suitable for enterprise knowledge management, intelligent Q&A systems, and information retrieval scenarios.

Architecture

🚀 Features

Private Data Search: Maximizes the utilization of enterprise internal data while ensuring data security. When necessary, it can integrate online content for more accurate answers.
Vector Database Management: Supports Milvus and other vector databases, allowing data partitioning for efficient retrieval.
Flexible Embedding Options: Compatible with multiple embedding models for optimal selection.
Multiple LLM Support: Supports DeepSeek, OpenAI, and other large models for intelligent Q&A and content generation.
Document Loader: Supports local file loading, with web crawling capabilities under development.

🎉 Demo

📖 Quick Start

Installation

Install DeepSearcher using one of the following methods:

Option 1: Using pip

Create and activate a virtual environment(Python 3.10 version is recommended).

python -m venv .venv
source .venv/bin/activate

Install DeepSearcher

pip install deepsearcher

For optional dependencies, e.g., ollama:

pip install "deepsearcher[ollama]"

Option 2: Install in Development Mode

We recommend using uv for faster and more reliable installation. Follow the offical installation instructions to install it.

Clone the repository and navigate to the project directory:

git clone https://github.com/zilliztech/deep-searcher.git && cd deep-searcher

Synchronize and install dependencies:

uv sync source .venv/bin/activate

For more detailed development setup and optional dependency installation options, see CONTRIBUTING.md.

Quick start demo

To run this quick start demo, please prepare your OPENAIAPIKEY in your environment variables. If you change the LLM in the configuration, make sure to prepare the corresponding API key.

from deepsearcher.configuration import Configuration, init_config
from deepsearcher.online_query import query
config = Configuration()
Customize your config here,
more configuration see the Configuration Details section below.
config.setproviderconfig("llm", "OpenAI", {"model": "o1-mini"})
config.setproviderconfig("embedding", "OpenAIEmbedding", {"model": "text-embedding-ada-002"})
init_config(config = config)
Load your local data
from deepsearcher.offlineloading import loadfromlocalfiles
loadfromlocalfiles(pathsordirectory=yourlocal_path)
(Optional) Load from web crawling (FIRECRAWLAPIKEY env variable required)
from deepsearcher.offlineloading import loadfrom_website
loadfromwebsite(urls=website_url)
Query
result = query("Write a report about xxx.") # Your question here

Configuration Details:

LLM Configuration

config.setproviderconfig("llm", "(LLMName)", "(Arguments dict)")

The "LLMName" can be one of the following: ["DeepSeek", "OpenAI", "XAI", "SiliconFlow", "Aliyun", "PPIO", "TogetherAI", "Gemini", "Ollama", "Novita", "Jiekou.AI"]

The "Arguments dict" is a dictionary that contains the necessary arguments for the LLM class.

Example (OpenAI)

Make sure you have prepared your OPENAI API KEY as an env variable OPENAIAPIKEY.

config.setproviderconfig("llm", "OpenAI", {"model": "o1-mini"})

More details about OpenAI models: https://platform.openai.com/docs/models

Example (Qwen3 from Aliyun Bailian)

Make sure you have prepared your Bailian API KEY as an env variable DASHSCOPEAPIKEY.

config.setproviderconfig("llm", "Aliyun", {"model": "qwen-plus-latest"})

More details about Aliyun Bailian models: https://bailian.console.aliyun.com

Example (Qwen3 from OpenRouter)

config.setproviderconfig("llm", "OpenAI", {"model": "qwen/qwen3-235b-a22b:free", "baseurl": "https://openrouter.ai/api/v1", "apikey": "OPENROUTERAPIKEY"})

More details about OpenRouter models: https://openrouter.ai/qwen/qwen3-235b-a22b:free

Example (DeepSeek from official)

Make sure you have prepared your DEEPSEEK API KEY as an env variable DEEPSEEKAPIKEY.

config.setproviderconfig("llm", "DeepSeek", {"model": "deepseek-reasoner"})

More details about DeepSeek: https://api-docs.deepseek.com/

Example (DeepSeek from SiliconFlow)

Make sure you have prepared your SILICONFLOW API KEY as an env variable SILICONFLOWAPIKEY.

config.setproviderconfig("llm", "SiliconFlow", {"model": "deepseek-ai/DeepSeek-R1"})

More details about SiliconFlow: https://docs.siliconflow.cn/quickstart

Example (DeepSeek from TogetherAI)

Make sure you have prepared your TOGETHER API KEY as an env variable TOGETHERAPIKEY.

For deepseek R1:

config.setproviderconfig("llm", "TogetherAI", {"model": "deepseek-ai/DeepSeek-R1"})

For Llama 4:

config.setproviderconfig("llm", "TogetherAI", {"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct"})

You need to install together before running, execute: pip install together. More details about TogetherAI: https://www.together.ai/

Example (XAI Grok)

Make sure you have prepared your XAI API KEY as an env variable XAIAPIKEY.

config.setproviderconfig("llm", "XAI", {"model": "grok-4-0709"})

More details about XAI Grok: https://docs.x.ai/docs/overview#featured-models

Example (Claude)

Make sure you have prepared your ANTHROPIC API KEY as an env variable ANTHROPICAPIKEY.

config.setproviderconfig("llm", "Anthropic", {"model": "claude-sonnet-4-0"})

More details about Anthropic Claude: https://docs.anthropic.com/en/home

Example (Google Gemini)

Make sure you have prepared your GEMINI API KEY as an env variable GEMINIAPIKEY.

config.setproviderconfig('llm', 'Gemini', { 'model': 'gemini-2.0-flash' })

You need to install gemini before running, execute: pip install google-genai. More details about Gemini: https://ai.google.dev/gemini-api/docs

Example (DeepSeek from PPIO)

Make sure you have prepared your PPIO API KEY as an env variable PPIOAPIKEY. You can create an API Key here.

config.setproviderconfig("llm", "PPIO", {"model": "deepseek/deepseek-r1-turbo"})

More details about PPIO: https://ppinfra.com/docs/get-started/quickstart.html?utmsource=githubdeep-searcher

Example (Claude Sonnet 4.5 from Jiekou.AI)

Make sure you have prepared your Jiekou.AI API KEY as an env variable JIEKOUAPIKEY. You can create an API Key here.

config.setproviderconfig("llm", "JiekouAI", {"model": "claude-sonnet-4-5-20250929"})

More details about Jiekou.AI: https://docs.jiekou.ai/docs/support/quickstart?utmsource=githubdeep-searcher

Example (Ollama)

Follow these instructions to set up and run a local Ollama instance:

Download and install Ollama onto the available supported platforms (including Windows Subsystem for Linux).

View a list of available models via the model library.

Fetch available LLM models via ollama pull <name-of-model>

Example: ollama pull qwen3

To chat directly with a model from the command line, use ollama run <name-of-model>.

By default, Ollama has a REST API for running and managing models on http://localhost:11434.

config.setproviderconfig("llm", "Ollama", {"model": "qwen3"})

Example (Volcengine)

Make sure you have prepared your Volcengine API KEY as an env variable VOLCENGINEAPIKEY. You can create an API Key here.

config.setproviderconfig("llm", "Volcengine", {"model": "deepseek-r1-250120"})

More details about Volcengine: https://www.volcengine.com/docs/82379/1099455?utmsource=githubdeep-searcher

Example (GLM)

Make sure you have prepared your GLM API KEY as an env variable GLMAPIKEY.

config.setproviderconfig("llm", "GLM", {"model": "glm-4-plus"})

You need to install zhipuai before running, execute: pip install zhipuai. More details about GLM: https://bigmodel.cn/dev/welcome

Example (Amazon Bedrock)

Make sure you have prepared your Amazon Bedrock API KEY as an env variable AWSACCESSKEYID and AWSSECRETACCESSKEY.

config.setproviderconfig("llm", "Bedrock", {"model": "us.deepseek.r1-v1:0"})

You need to install boto3 before running, execute: pip install boto3. More details about Amazon Bedrock: https://docs.aws.amazon.com/bedrock/

Example (IBM watsonx.ai)

Make sure you have prepared your watsonx.ai credentials as env variables WATSONXAPIKEY, WATSONXURL, and WATSONXPROJECTID.

config.setproviderconfig("llm", "watsonx", {"model": "us.deepseek.r1-v1:0"})

You need to install ibm-watsonx-ai before running, execute: pip install ibm-watsonx-ai. More details about IBM watsonx.ai: https://www.ibm.com/products/watsonx-ai/foundation-models

Embedding Model Configuration

config.setproviderconfig("embedding", "(EmbeddingModelName)", "(Arguments dict)")

The "EmbeddingModelName" can be one of the following: ["MilvusEmbedding", "OpenAIEmbedding", "VoyageEmbedding", "SiliconflowEmbedding", "PPIOEmbedding", "NovitaEmbedding", "JiekouAIEmbedding"]

The "Arguments dict" is a dictionary that contains the necessary arguments for the embedding model class.

Example (OpenAI embedding)

Make sure you have prepared your OpenAI API KEY as an env variable OPENAIAPIKEY.

config.setproviderconfig("embedding", "OpenAIEmbedding", {"model": "text-embedding-3-small"})

More details about OpenAI models: https://platform.openai.com/docs/guides/embeddings/use-cases

Example (OpenAI embedding Azure)

Make sure you have prepared your OpenAI API KEY as an env variable OPENAIAPIKEY.

config.setproviderconfig("embedding", "OpenAIEmbedding", {     "model": "text-embedding-ada-002",     "azure_endpoint": "https://.openai.azure.com/",     "api_version": "2023-05-15" })

Example (Pymilvus built-in embedding model)

Use the built-in embedding model in Pymilvus, you can set the model name as "default", "BAAI/bge-base-en-v1.5", "BAAI/bge-large-en-v1.5", "jina-embeddings-v3", etc.
See milvus_embedding.py for more details.

config.setproviderconfig("embedding", "MilvusEmbedding", {"model": "BAAI/bge-base-en-v1.5"})

config.setproviderconfig("embedding", "MilvusEmbedding", {"model": "jina-embeddings-v3"})

For Jina's embedding model, you needJINAAIAPIKEY.

You need to install pymilvus model before running, execute: pip install pymilvus.model. More details about Pymilvus: https://milvus.io/docs/embeddings.md

Example (VoyageAI embedding)

Make sure you have prepared your VOYAGE API KEY as an env variable VOYAGEAPIKEY.

config.setproviderconfig("embedding", "VoyageEmbedding", {"model": "voyage-3"})

You need to install voyageai before running, execute: pip install voyageai. More details about VoyageAI: https://docs.voyageai.com/embeddings/

Example (Amazon Bedrock embedding)

config.setproviderconfig("embedding", "BedrockEmbedding", {"model": "amazon.titan-embed-text-v2:0"})

You need to install boto3 before running, execute: pip install boto3. More details about Amazon Bedrock: https://docs.aws.amazon.com/bedrock/

Example (Novita AI embedding)

Make sure you have prepared your Novita AI API KEY as an env variable NOVITAAPIKEY.

config.setproviderconfig("embedding", "NovitaEmbedding", {"model": "baai/bge-m3"})

More details about Novita AI: https://novita.ai/docs/api-reference/model-apis-llm-create-embeddings?utmsource=githubdeep-searcher&utmmedium=githubreadme&utm_campaign=link

Example (Siliconflow embedding)

Make sure you have prepared your Siliconflow API KEY as an env variable SILICONFLOWAPIKEY.

config.setproviderconfig("embedding", "SiliconflowEmbedding", {"model": "BAAI/bge-m3"})

More details about Siliconflow: https://docs.siliconflow.cn/en/api-reference/embeddings/create-embeddings

Example (Volcengine embedding)

Make sure you have prepared your Volcengine API KEY as an env variable VOLCENGINEAPIKEY.

config.setproviderconfig("embedding", "VolcengineEmbedding", {"model": "doubao-embedding-text-240515"})

More details about Volcengine: https://www.volcengine.com/docs/82379/1302003

Example (GLM embedding)

Make sure you have prepared your GLM API KEY as an env variable GLMAPIKEY.

config.setproviderconfig("embedding", "GLMEmbedding", {"model": "embedding-3"})

You need to install zhipuai before running, execute: pip install zhipuai. More details about GLM: https://bigmodel.cn/dev/welcome

Example (Google Gemini embedding)

Make sure you have prepared your Gemini API KEY as an env variable GEMINIAPIKEY.

config.setproviderconfig("embedding", "GeminiEmbedding", {"model": "text-embedding-004"})

You need to install gemini before running, execute: pip install google-genai. More details about Gemini: https://ai.google.dev/gemini-api/docs

Example (Ollama embedding)

config.setproviderconfig("embedding", "OllamaEmbedding", {"model": "bge-m3"})

You need to install ollama before running, execute: pip install ollama. More details about Ollama Python SDK: https://github.com/ollama/ollama-python

Example (PPIO embedding)

Make sure you have prepared your PPIO API KEY as an env variable PPIOAPIKEY.

config.setproviderconfig("embedding", "PPIOEmbedding", {"model": "baai/bge-m3"})

More details about PPIO: https://ppinfra.com/docs/get-started/quickstart.html?utmsource=githubdeep-searcher

Example (Jiekou.AI embedding)

Make sure you have prepared your Jiekou.AI API KEY as an env variable JIEKOUAPIKEY.

config.setproviderconfig("embedding", "JiekouAIEmbedding", {"model": "qwen/qwen3-embedding-8b"})

More details about Jiekou.AI: https://docs.jiekou.ai/docs/support/quickstart?utmsource=githubdeep-searcher

Example (FastEmbed embedding)

config.setproviderconfig("embedding", "FastEmbedEmbedding", {"model": "intfloat/multilingual-e5-large"})

You need to install fastembed before running, execute: pip install fastembed. More details about fastembed: https://github.com/qdrant/fastembed

Example (IBM watsonx.ai embedding)

Make sure you have prepared your WatsonX credentials as env variables WATSONXAPIKEY, WATSONXURL, and WATSONXPROJECTID.

config.setproviderconfig("embedding", "WatsonXEmbedding", {"model": "ibm/slate-125m-english-rtrvr-v2"})

config.setproviderconfig("embedding", "WatsonXEmbedding", {"model": "sentence-transformers/all-minilm-l6-v2"})

You need to install ibm-watsonx-ai before running, execute: pip install ibm-watsonx-ai. More details about IBM watsonx.ai: https://www.ibm.com/products/watsonx-ai/foundation-models

Vector Database Configuration

config.setproviderconfig("vector_db", "(VectorDBName)", "(Arguments dict)")

The "VectorDBName" can be one of the following: ["Milvus"] (Under development)

The "Arguments dict" is a dictionary that contains the necessary arguments for the Vector Database class.

Example (Milvus)

config.setproviderconfig("vector_db", "Milvus", {"uri": "./milvus.db", "token": ""})

More details about Milvus Config:

Setting the uri as a local file, e.g. ./milvus.db, is the most convenient method, as it automatically utilizes Milvus Lite to store all data in this file.

If you have a large-scale dataset, you can set up a more performant Milvus server using Docker or Kubernetes. In this setup, use the server URI, e.g., http://localhost:19530, as your uri. You can also use any other connection parameters supported by Milvus such as host, user, password, or secure.

If you want to use Zilliz Cloud, the fully managed cloud service for Milvus, adjust the uri and token according to the Public Endpoint and API Key in Zilliz Cloud.

Example (AZURE AI Search)

config.setproviderconfig("vector_db", "AzureSearch", {     "endpoint": "https://.search.windows.net",     "index_name": "",     "api_key": "",     "vector_field": "" })

More details about Milvus Config:

File Loader Configuration

config.setproviderconfig("file_loader", "(FileLoaderName)", "(Arguments dict)")

The "FileLoaderName" can be one of the following: ["PDFLoader", "TextLoader", "UnstructuredLoader"]

The "Arguments dict" is a dictionary that contains the necessary arguments for the File Loader class.

Example (Unstructured)

You can use Unstructured in two ways:

With API: Set environment variables UNSTRUCTUREDAPIKEY and UNSTRUCTUREDAPIURL

Without API: Use the local processing mode by simply not setting these environment variables

config.setproviderconfig("file_loader", "UnstructuredLoader", {})

Currently supported file types: ["pdf"] (Under development)

Installation requirements:
- Install ingest pipeline: pip install unstructured-ingest
- For all document formats: pip install "unstructured[all-docs]"
- For specific formats (e.g., PDF only): pip install "unstructured[pdf]"

More information:
- Unstructured documentation: https://docs.unstructured.io/ingestion/overview
- Installation guide: https://docs.unstructured.io/open-source/installation/full-installation

Example (Docling)

config.setproviderconfig("file_loader", "DoclingLoader", {})

Currently supported file types: please refer to the Docling documentation: https://docling-project.github.io/docling/usage/supported_formats/#supported-output-formats

You need to install docling before running, execute: pip install docling. More details about Docling: https://docling-project.github.io/docling/

Web Crawler Configuration

config.setproviderconfig("web_crawler", "(WebCrawlerName)", "(Arguments dict)")

The "WebCrawlerName" can be one of the following: ["FireCrawlCrawler", "Crawl4AICrawler", "JinaCrawler"]

The "Arguments dict" is a dictionary that contains the necessary arguments for the Web Crawler class.

Example (FireCrawl)

Make sure you have prepared your FireCrawl API KEY as an env variable FIRECRAWLAPIKEY.

config.setproviderconfig("web_crawler", "FireCrawlCrawler", {})

More details about FireCrawl: https://docs.firecrawl.dev/introduction

Example (Crawl4AI)

Make sure you have run crawl4ai-setup in your environment.

config.setproviderconfig("webcrawler", "Crawl4AICrawler", {"browserconfig": {"headless": True, "verbose": True}})

You need to install crawl4ai before running, execute: pip install crawl4ai. More details about Crawl4AI: https://docs.crawl4ai.com/

Example (Jina Reader)

Make sure you have prepared your Jina Reader API KEY as an env variable JINAAPITOKEN or JINAAIAPIKEY.

config.setproviderconfig("web_crawler", "JinaCrawler", {})

More details about Jina Reader: https://jina.ai/reader/

Example (Docling)

config.setproviderconfig("web_crawler", "DoclingCrawler", {})

Currently supported file types: please refer to the Docling documentation: https://docling-project.github.io/docling/usage/supported_formats/#supported-output-formats

You need to install docling before running, execute: pip install docling. More details about Docling: https://docling-project.github.io/docling/

Python CLI Mode

Load

deepsearcher load "yourlocalpathorurl"
load into a specific collection
deepsearcher load "yourlocalpathorurl" --collectionname "yourcollectionname" --collectiondesc "yourcollectiondescription"

Example loading from local file:

deepsearcher load "/path/to/your/local/file.pdf"
or more files at once
deepsearcher load "/path/to/your/local/file1.pdf" "/path/to/your/local/file2.md"

Example loading from url (Set FIRECRAWLAPIKEY in your environment variables, see FireCrawl for more details):

deepsearcher load "https://www.wikiwand.com/en/articles/DeepSeek"

Query

deepsearcher query "Write a report about xxx."

More help information

deepsearcher --help

For more help information about a specific subcommand, you can use deepsearcher [subcommand] --help.

deepsearcher load --help deepsearcher query --help

Deployment

Configure modules

You can configure all arguments by modifying config.yaml to set up your system with default modules. For example, set your OPENAIAPIKEY in the llm section of the YAML file.

Start service

The main script will run a FastAPI service with default address localhost:8000.

$ python main.py

Access via browser

You can open url http://localhost:8000/docs in browser to access the web service. Click on the button "Try it out", it allows you to fill the parameters and directly interact with the API.

❓ Q&A

Q1: Why I failed to parse LLM output format / How to select the LLM?

A1: Small LLMs struggle to follow the prompt to generate a desired response, which usually cause the format parsing problem. A better practice is to use large reasoning models e.g. deepseek-r1 671b, OpenAI o-series, Claude 4 sonnet, etc. as your LLM.

Q2: OSError: We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like GPTCache/paraphrase-albert-small-v2 is not the path to a directory containing a file named config.json. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.

A2: This is mainly due to abnormal access to huggingface, which may be a network or permission problem. You can try the following two methods:

If there is a network problem, set up a proxy, try adding the following environment variable.

export HF_ENDPOINT=https://hf-mirror.com

If there is a permission problem, set up a personal token, try adding the following environment variable.

export HUGGINGFACEHUB_TOKEN=xxxx

Q3: DeepSearcher doesn't run in Jupyter notebook.

A3: Install nest_asyncio and then put this code block in front of your jupyter notebook.

pip install nest_asyncio

import nest_asyncio
nest_asyncio.apply()

🔧 Module Support

🔹 Embedding Models

Open-source embedding models
OpenAI (OPENAIAPI_KEY env variable required)
VoyageAI (VOYAGEAPI_KEY env variable required)
Amazon Bedrock (AWSACCESSKEYID and AWSSECRETACCESS_KEY env variable required)
FastEmbed
PPIO (PPIOAPI_KEY env variable required)
Novita AI (NOVITAAPIKEY env variable required)
IBM watsonx.ai (WATSONXAPIKEY, WATSONXURL, WATSONXPROJECT_ID env variables required)
Jiekou.AI (JIEKOUAPI_KEY env variable required)

🔹 LLM Support

OpenAI (OPENAIAPI_KEY env variable required)
DeepSeek (DEEPSEEKAPI_KEY env variable required)
XAI Grok (XAIAPI_KEY env variable required)
Anthropic Claude (ANTHROPICAPI_KEY env variable required)
SiliconFlow Inference Service (SILICONFLOWAPI_KEY env variable required)
PPIO (PPIOAPI_KEY env variable required)
TogetherAI Inference Service (TOGETHERAPI_KEY env variable required)
Google Gemini (GEMINIAPI_KEY env variable required)
SambaNova Cloud Inference Service (SAMBANOVAAPI_KEY env variable required)
Ollama
Novita AI (NOVITAAPIKEY env variable required)
IBM watsonx.ai (WATSONXAPIKEY, WATSONXURL, WATSONXPROJECT_ID env variable required)
Jiekou.AI (JIEKOUAPI_KEY env variable required)

🔹 Document Loader

Local File

- PDF(with txt/md) loader - Unstructured (under development) (UNSTRUCTUREDAPIKEY and UNSTRUCTUREDURL env variables required)

Web Crawler

- FireCrawl (FIRECRAWLAPI_KEY env variable required) - Jina Reader (JINAAPI_TOKEN env variable required) - Crawl4AI (You should run command crawl4ai-setup for the first time)