Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Danswer is the AI Assistant that can be connected to many sources like Atlassian Confluence, Sharepoint, Slack, web, files, MS Teams and many more sources. It performs retrieval of documents, generates embeddings and stores them locally. Once a query comes in, a semantic similarity search is performed and the most relevant results are passed to the LLM instead of full documents, by doing this, noise to the model is reduced (System Overview).

...

  1. Clone the Danswer repo:

    Code Block
    git clone https://github.com/danswer-ai/danswer.git
  2. Go to danswer/deployment/docker_compose:

  3. Code Block
    cd danswer/deployment/docker_compose
  4. Configure Danswer by creating a file in danswer/deployment/docker_compose/.env with the following contents:

    Code Block
    # Configures basic email/password based login
    AUTH_TYPE="basic"
    
    # Rephrasing the query into different languages to improve search recall
    MULTILINGUAL_QUERY_EXPANSION="English,Spanish"
    
    # Set a cheaper/faster LLM for the flows that are easier (such as translating the query etc.)
    FAST_GEN_AI_MODEL_VERSION="gpt-3.5-turbo"
    
    # Setting more verbose logging
    LOG_LEVEL="debug"
    LOG_ALL_MODEL_INTERACTIONS="true"
    
    DISABLE_TELEMETRY="true"
    1. More information about configuration settings can be found here https://docs.danswer.dev/configuration_guide

  5. Build the containers:

    Code Block
    docker compose -f docker-compose.dev.yml -p danswer-stack up -d --build --force-recreate
  6. Danswer will now be running on http://{ip-address}:3000.

  7. To stop the stack:

    Code Block
    docker compose -f docker-compose.dev.yml -p danswer-stack down
  8. (Optional) If you are using Ollama on the same instance, use the following settings:

    1. Display name: ollama

    2. Provider Name: ollama

    3. [Optional] API Base: http://host.docker.internal:11434

    4. Model Names:

      1. llama3

      2. phi3

    5. Default model: llama3

    6. Fast Model: phi3

  9. (Optional) If you are using remote inference like OpenAI or Azure OpenAI, refer to the official danswer.ai docs: https://docs.danswer.dev/quickstart#generative-ai-api-key

  10. Create your first connector (https://docs.danswer.dev/connectors/overview )

...