That’s it! You’re ready to use Morphik now :)

​

Direct Installation

git clone https://github.com/morphik-org/morphik-core.git

ls morphik-core

cd morphik-core

python3.12 -m venv .venv

source .venv/bin/activate

source .venv/bin/activate

.venv\Scripts\activate.bat

.venv\Scripts\Activate.ps1

Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

pip install -r requirements.txt

# If using Python 3.12+, you might need a specific version of unstructured
pip install unstructured==0.16.10

# Download required NLTK resources
python -m nltk.downloader averaged_perceptron_tagger punkt

cp .env.example .env

python quick_setup.py

python start_server.py

INFO:     Started server process [15169]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://localhost:8000 (Press CTRL+C to quit)

​

Using Docker

Morphik provides a streamlined Docker-based setup that includes all necessary components: the core API, PostgreSQL with pgvector, and Ollama for AI models.

​

Prerequisites

• Docker and Docker Compose installed on your system
• At least 10GB of free disk space (for models and data)
• 8GB+ RAM recommended

​

Quick Start

1. Clone the repository and navigate to the project directory:

git clone https://github.com/morphik-org/morphik-core.git
cd morphik-core

2. Before first-time setup, check the configuration:

Ensure your morphik.toml file has the correct settings for running in Docker:

# For Redis configuration when using Docker
[redis]
host = "redis"  # use "redis" when running in Docker (not "localhost")
port = 6379

(If using local models with Ollama) Also ensure the Ollama configuration matches your deployment setup:

• If running both Morphik and Ollama as Docker containers:

# If you are running on docker and ollama is also running on docker use the following
ollama_llama_docker_docker = { model_name = "ollama_chat/llama3.2", api_base = "http://ollama:11434" }
ollama_llama_vision_docker_docker = { model_name = "ollama_chat/llama3.2-vision", api_base = "http://ollama:11434", vision = true }

# For embedding models
ollama_embedding_docker_docker = { model_name = "ollama/nomic-embed-text", api_base = "http://ollama:11434" }

• If running Morphik in Docker but Ollama locally:

# If you are running on docker, but running ollama locally use the following
ollama_llama_docker = { model_name = "ollama_chat/llama3.2", api_base = "http://host.docker.internal:11434" }
ollama_llama_vision_docker = { model_name = "ollama_chat/llama3.2-vision", api_base = "http://host.docker.internal:11434", vision = true }

# For embedding models
ollama_embedding_docker = { model_name = "ollama/nomic-embed-text", api_base = "http://host.docker.internal:11434" }

And update the active model references to use the appropriate Docker configurations:

[completion]
model = "ollama_llama_vision_docker_docker"  # If both in Docker

[embedding]
model = "ollama_embedding_docker_docker"  # If both in Docker

If you want to use Ollama for AI capabilities (recommended for local development):

docker compose --profile ollama up --build -d

This will build docker with an Ollama container.

Or if you’re using OpenAI, Anthropic, or other models (configure the API key in .env):

docker compose up --build

This will build docker without the Ollama container.

These commands will:

• Build all required containers
• Download necessary AI models (nomic-embed-text and llama3.2 if using Ollama)
• Initialize the PostgreSQL database with pgvector
• Start all services

The initial setup may take 5-10 minutes depending on your internet speed, as it needs to download the AI models.

Note: When using Ollama, ensure your system has sufficient memory. The llama3.2 model requires at least 4GB of available RAM. If you encounter memory issues, you can increase Docker’s memory allocation in Docker Desktop settings (Resources > Advanced > Memory), modify the morphik.toml file to use a smaller model, or switch to using OpenAI API.

docker compose up    # Start all services
docker compose down  # Stop all services

1. To completely reset (will delete all data and models):

docker compose down -v

​

Configuration

The default configuration works out of the box and includes:

• PostgreSQL with pgvector for document storage
• Ollama for AI models (embeddings and completions)
• Local file storage
• Basic authentication

You can customize your setup by creating a .env file:

JWT_SECRET_KEY=your-secure-key-here  # Important: Change in production
OPENAI_API_KEY=sk-...                # Only if using OpenAI
HOST=0.0.0.0                         # Leave as is for Docker
PORT=8000                            # Change if needed

​

Accessing Services

• Morphik API: http://localhost:8000
• API Documentation: http://localhost:8000/docs
• Health Check: http://localhost:8000/health

​

Troubleshooting

1. Service Won’t Start

   # View all logs
   docker compose logs
   
   # View specific service logs
   docker compose logs morphik
   docker compose logs postgres
   docker compose logs ollama
   

2. Database Issues

   • Check PostgreSQL is healthy: docker compose ps
   • Verify database connection: docker compose exec postgres psql -U morphik -d morphik

3. Model Download Issues

   • Check Ollama logs: docker compose logs ollama
   • Ensure enough disk space for models
   • Try restarting Ollama: docker compose restart ollama
   • Verify that your Redis and Ollama configuration in morphik.toml matches your deployment:
     • For Redis in Docker, use host = "redis" (not “localhost”)
     • If running Ollama in Docker, use http://ollama:11434 endpoint
     • If running Ollama locally but Morphik in Docker, use http://host.docker.internal:11434

4. Ollama Memory Issues

   • If you see errors like “model requires more system memory than is available” in the logs:

     • Increase Docker memory allocation in Docker Desktop:
       1. Open Docker Desktop application
       2. Click on Settings (gear icon)
       3. Go to “Resources” section
       4. Increase memory allocation to at least 6GB (8GB recommended)
       5. Click “Apply & Restart”
     • Alternatively, modify morphik.toml to use a smaller model
     • Or switch to OpenAI API by uncommenting the OpenAI sections in morphik.toml

   • For knowledge graph creation specifically, you can switch from Ollama to OpenAI:

     # Change this section in morphik.toml
     [graph]
     provider = "openai"
     model_name = "gpt-4o-mini"
     enable_entity_resolution = true
     

5. Performance Issues

   • Monitor resources: docker stats
   • Ensure sufficient RAM (8GB+ recommended)
   • Check disk space: df -h

python3.12 -m venv .venv

source .venv/bin/activate

pip install morphik

from morphik import Morphik

# Initialize the Morphik client
morphik = Morphik(uri="your-morphik-uri")
# Ingest a file
doc = morphik.ingest_file(file_path="super/complex/file.pdf")
doc.wait_for_completion()

# Query the file
response = morphik.query(query="What percentage of Morphik users are building something cool?")
print(response) # Responds with 100% :)

You can find our entire SDK documentation here.

You can find more information about MCP here.