Fully local web research and report writing assistant

Ollama Deep Researcher is a fully local web research assistant that uses any LLM hosted by Ollama. Give it a topic and it will generate a web search query, gather web search results (via Tavily by default), summarize the results of web search, reflect on the summary to examine knowledge gaps, generate a new search query to address the gaps, search, and improve the summary for a user-defined number of cycles. It will provide the user a final markdown summary with all sources used.

Short summary:

See it in action or build it yourself? Check out these helpful video tutorials:

• Overview of Ollama Deep Researcher with R1 - Load and test DeepSeek R1 distilled models.
• Building Ollama Deep Researcher from Scratch - Overview of how this is built.

1. Download the Ollama app for Mac here.

2. Pull a local LLM from Ollama. As an example:

ollama pull deepseek-r1:8b

3. Clone the repository:

git clone https://github.com/langchain-ai/ollama-deep-researcher.git
cd ollama-deep-researcher

4. Select a web search tool:

By default, it will use DuckDuckGo for web search, which does not require an API key. But you can also use Tavily or Perplexity by adding their API keys to the environment file:

cp .env.example .env

The following environment variables are supported:

• OLLAMA_BASE_URL - the endpoint of the Ollama service, defaults to http://localhost:11434 if not set
• OLLAMA_MODEL - the model to use, defaults to llama3.2 if not set
• SEARCH_API - the search API to use, either duckduckgo (default) or tavily or perplexity. You need to set the corresponding API key if tavily or perplexity is used.
• TAVILY_API_KEY - the tavily API key to use
• PERPLEXITY_API_KEY - the perplexity API key to use
• MAX_WEB_RESEARCH_LOOPS - the maximum number of research loop steps, defaults to 3
• FETCH_FULL_PAGE - fetch the full page content if using duckduckgo for the search API, defaults to false

5. (Recommended) Create a virtual environment:

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

6. Launch the assistant with the LangGraph server:

# Install uv package manager
curl -LsSf https://astral.sh/uv/install.sh | sh
uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.11 langgraph dev

1. Download the Ollama app for Windows here.

2. Pull a local LLM from Ollama. As an example:

ollama pull deepseek-r1:8b

3. Clone the repository:

git clone https://github.com/langchain-ai/ollama-deep-researcher.git
cd ollama-deep-researcher

4. Select a web search tool, as above.

5. (Recommended) Create a virtual environment: Install Python 3.11 (and add to PATH during installation). Restart your terminal to ensure Python is available, then create and activate a virtual environment:

python -m venv .venv
.venv\Scripts\Activate.ps1

6. Launch the assistant with the LangGraph server:

# Install dependencies
pip install -e .
pip install -U "langgraph-cli[inmem]"            

# Start the LangGraph server
langgraph dev

When you launch LangGraph server, you should see the following output and Studio will open in your browser:

Ready!

API: http://127.0.0.1:2024

Docs: http://127.0.0.1:2024/docs

LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024

Open LangGraph Studio Web UI via the URL in the output above.

In the configuration tab:

• Pick your web search tool (DuckDuckGo, Tavily, or Perplexity) (it will by default be DuckDuckGo)
• Set the name of your local LLM to use with Ollama (it will by default be llama3.2)
• You can set the depth of the research iterations (it will by default be 3)

Give the assistant a topic for research, and you can visualize its process!

When selecting a local LLM, note that this application relies on the model's ability to produce structured JSON output. Some models may have difficulty with this requirement:

• Working well:

  • Llama2 3.2
  • DeepSeek R1 (8B)

• Known issues:

  • DeepSeek R1 (7B) - Currently has difficulty producing required JSON output

If you encounter JSON-related errors (e.g., KeyError: 'query'), try switching to one of the confirmed working models.

When accessing the LangGraph Studio UI:

• Firefox is recommended for the best experience
• Safari users may encounter security warnings due to mixed content (HTTPS/HTTP)
• If you encounter issues, try:
  1. Using Firefox or another browser
  2. Disabling ad-blocking extensions
  3. Checking browser console for specific error messages

Ollama Deep Researcher is inspired by IterDRAG. This approach will decompose a query into sub-queries, retrieve documents for each one, answer the sub-query, and then build on the answer by retrieving docs for the second sub-query. Here, we do similar:

• Given a user-provided topic, use a local LLM (via Ollama) to generate a web search query
• Uses a search engine (configured for DuckDuckGo, Tavily, or Perplexity) to find relevant sources
• Uses LLM to summarize the findings from web search related to the user-provided research topic
• Then, it uses the LLM to reflect on the summary, identifying knowledge gaps
• It generates a new search query to address the knowledge gaps
• The process repeats, with the summary being iteratively updated with new information from web search
• It will repeat down the research rabbit hole
• Runs for a configurable number of iterations (see configuration tab)

The output of the graph is a markdown file containing the research summary, with citations to the sources used.

All sources gathered during research are saved to the graph state.

You can visualize them in the graph state, which is visible in LangGraph Studio:

The final summary is saved to the graph state as well:

There are various ways to deploy this graph.

See Module 6 of LangChain Academy for a detailed walkthrough of deployment options with LangGraph.

A TypeScript port of this project (without Perplexity search) is available at: https://github.com/PacoVK/ollama-deep-researcher-ts

The included Dockerfile only runs LangChain Studio with ollama-deep-researcher as a service, but does not include Ollama as a dependant service. You must run Ollama separately and configure the OLLAMA_BASE_URL environment variable. Optionally you can also specify the Ollama model to use by providing the OLLAMA_MODEL environment variable.

Clone the repo and build an image:

$ docker build -t ollama-deep-researcher .

Run the container:

$ docker run --rm -it -p 2024:2024 \
  -e SEARCH_API="tavily" \ 
  -e TAVILY_API_KEY="tvly-***YOUR_KEY_HERE***" \
  -e OLLAMA_BASE_URL="http://host.docker.internal:11434/" \
  -e OLLAMA_MODEL="llama3.2" \  
  ollama-deep-researcher

NOTE: You will see log message:

2025-02-10T13:45:04.784915Z [info     ] 🎨 Opening Studio in your browser... [browser_opener] api_variant=local_dev message=🎨 Opening Studio in your browser...
URL: https://smith.langchain.com/studio/?baseUrl=http://0.0.0.0:2024

...but the browser will not launch from the container.

Instead, visit this link with the correct baseUrl IP address: https://smith.langchain.com/studio/thread?baseUrl=http://127.0.0.1:2024