Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up

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

License

NotificationsYou must be signed in to change notification settings

zilliztech/deep-searcher

Repository files navigation

DeepSearcher

LicenseTwitterdiscord

DeepSearcher combines cutting-edge LLMs (OpenAI o3, Qwen3, DeepSeek, Grok 3, Claude 3.7 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

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 .venvsource .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 usinguv for faster and more reliable installation. Follow theoffical 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 syncsource .venv/bin/activate

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

Quick start demo

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

fromdeepsearcher.configurationimportConfiguration,init_configfromdeepsearcher.online_queryimportqueryconfig=Configuration()# Customize your config here,# more configuration see the Configuration Details section below.config.set_provider_config("llm","OpenAI", {"model":"o1-mini"})config.set_provider_config("embedding","OpenAIEmbedding", {"model":"text-embedding-ada-002"})init_config(config=config)# Load your local datafromdeepsearcher.offline_loadingimportload_from_local_filesload_from_local_files(paths_or_directory=your_local_path)# (Optional) Load from web crawling (`FIRECRAWL_API_KEY` env variable required)fromdeepsearcher.offline_loadingimportload_from_websiteload_from_website(urls=website_url)# Queryresult=query("Write a report about xxx.")# Your question here

Configuration Details:

LLM Configuration

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

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

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 variableOPENAI_API_KEY.

config.set_provider_config("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 variableDASHSCOPE_API_KEY.

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

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

Example (Qwen3 from OpenRouter)
config.set_provider_config("llm", "OpenAI", {"model": "qwen/qwen3-235b-a22b:free", "base_url": "https://openrouter.ai/api/v1", "api_key": "OPENROUTER_API_KEY"})

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 variableDEEPSEEK_API_KEY.

config.set_provider_config("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 variableSILICONFLOW_API_KEY.

config.set_provider_config("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 variableTOGETHER_API_KEY.

For deepseek R1:
config.set_provider_config("llm", "TogetherAI", {"model": "deepseek-ai/DeepSeek-R1"})
For Llama 4:
config.set_provider_config("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 variableXAI_API_KEY.

config.set_provider_config("llm", "XAI", {"model": "grok-2-latest"})

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 variableANTHROPIC_API_KEY.

config.set_provider_config("llm", "Anthropic", {"model": "claude-3-7-sonnet-latest"})

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 variableGEMINI_API_KEY.

config.set_provider_config('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 variablePPIO_API_KEY. You can create an API Keyhere.

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

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

Example (Ollama)

Followthese 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 themodel library.

Fetch available LLM models viaollama pull <name-of-model>

Example:ollama pull qwen3

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

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

config.set_provider_config("llm", "Ollama", {"model": "qwen3"})
Example (Volcengine)

Make sure you have prepared your Volcengine API KEY as an env variableVOLCENGINE_API_KEY. You can create an API Keyhere.

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

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

Example (GLM)

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

config.set_provider_config("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 variableAWS_ACCESS_KEY_ID andAWS_SECRET_ACCESS_KEY.

config.set_provider_config("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/

Embedding Model Configuration

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

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

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 variableOPENAI_API_KEY.

config.set_provider_config("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 variableOPENAI_API_KEY.

config.set_provider_config("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](deepsearcher/embedding/milvus_embedding.py) for more details.

config.set_provider_config("embedding", "MilvusEmbedding", {"model": "BAAI/bge-base-en-v1.5"})
config.set_provider_config("embedding", "MilvusEmbedding", {"model": "jina-embeddings-v3"})

For Jina's embedding model, you needJINAAI_API_KEY.

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 variableVOYAGE_API_KEY.

config.set_provider_config("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.set_provider_config("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 variableNOVITA_API_KEY.

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

More details about Novita AI:https://novita.ai/docs/api-reference/model-apis-llm-create-embeddings?utm_source=github_deep-searcher&utm_medium=github_readme&utm_campaign=link

Example (Siliconflow embedding)

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

config.set_provider_config("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 variableVOLCENGINE_API_KEY.

config.set_provider_config("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 variableGLM_API_KEY.

config.set_provider_config("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 variableGEMINI_API_KEY.

config.set_provider_config("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.set_provider_config("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 variablePPIO_API_KEY.

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

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

Vector Database Configuration

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

More details about Milvus Config:

  • Setting theuri as a local file, e.g../milvus.db, is the most convenient method, as it automatically utilizesMilvus Lite to store all data in this file.
  • If you have a large-scale dataset, you can set up a more performant Milvus server usingDocker or Kubernetes. In this setup, use the server URI, e.g.,http://localhost:19530, as youruri.
Example (AZURE AI Search)
config.set_provider_config("vector_db", "AzureSearch", {    "endpoint": "https://.search.windows.net",    "index_name": "",    "api_key": "",    "vector_field": ""})

More details about Milvus Config:

File Loader Configuration

config.set_provider_config("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 variablesUNSTRUCTURED_API_KEY andUNSTRUCTURED_API_URL
  • Without API: Use the local processing mode by simply not setting these environment variables
config.set_provider_config("file_loader", "UnstructuredLoader", {})
Example (Docling)
config.set_provider_config("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.set_provider_config("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 variableFIRECRAWL_API_KEY.

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

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

Example (Crawl4AI)

Make sure you have runcrawl4ai-setup in your environment.

config.set_provider_config("web_crawler", "Crawl4AICrawler", {"browser_config": {"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 variableJINA_API_TOKEN orJINAAI_API_KEY.

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

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

Example (Docling)
config.set_provider_config("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"your_local_path_or_url"# load into a specific collectiondeepsearcher load"your_local_path_or_url" --collection_name"your_collection_name" --collection_desc"your_collection_description"

Example loading from local file:

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

Example loading from url (SetFIRECRAWL_API_KEY in your environment variables, seeFireCrawl 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 usedeepsearcher [subcommand] --help.

deepsearcher load --helpdeepsearcher query --help

Deployment

Configure modules

You can configure all arguments by modifyingconfig.yaml to set up your system with default modules.For example, set yourOPENAI_API_KEY in thellm section of the YAML file.

Start service

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

$ python main.py

Access via browser

You can open urlhttp://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 3.7 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:

  1. If there is a network problem, set up a proxy, try adding the following environment variable.
export HF_ENDPOINT=https://hf-mirror.com
  1. If there is a permission problem, set up a personal token, try adding the following environment variable.
export HUGGING_FACE_HUB_TOKEN=xxxx

Q3: DeepSearcher doesn't run in Jupyter notebook.

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

pip install nest_asyncio
import nest_asyncionest_asyncio.apply()

🔧 Module Support

🔹 Embedding Models

🔹 LLM Support

🔹 Document Loader

  • Local File
    • PDF(with txt/md) loader
    • Unstructured (under development) (UNSTRUCTURED_API_KEY andUNSTRUCTURED_URL env variables required)
  • Web Crawler
    • FireCrawl (FIRECRAWL_API_KEY env variable required)
    • Jina Reader (JINA_API_TOKEN env variable required)
    • Crawl4AI (You should run commandcrawl4ai-setup for the first time)

🔹 Vector Database Support

📊 Evaluation

See theEvaluation directory for more details.

📌 Future Plans

  • Enhance web crawling functionality
  • Support more vector databases (e.g., FAISS...)
  • Add support for additional large models
  • Provide RESTful API interface (DONE)

We welcome contributions! Star & Fork the project and help us build a more powerful DeepSearcher! 🎯

[8]ページ先頭
©2009-2025 Movatter.jp