​
Morphik Configuration Guide

Morphik’s behavior can be fully customized through the databridge.toml configuration file. This file is the central place to configure all aspects of the system, from API settings to model providers, database connections, and processing options.

​
Configuration Basics

The databridge.toml file uses the TOML format (Tom’s Obvious Minimal Language) to organize settings into logical sections. Each section controls a specific component of the Morphik system:

[section_name]
setting1 = "value1"
setting2 = 123

When you first set up Morphik, you can:

  • Run python quick_setup.py for an interactive setup process
  • Copy and modify the example databridge.toml file
  • Create your own configuration file manually

​
Core Configuration Sections

​
API Server Settings

Controls how the API server runs:

[api]
host = "localhost"  # Use "0.0.0.0" for Docker
port = 8000
reload = true       # Hot reload for development

​
Authentication

Controls user authentication and permissions:

[auth]
jwt_algorithm = "HS256"
dev_mode = true  # Enables simplified auth for local development
dev_entity_id = "dev_user"
dev_entity_type = "developer"
dev_permissions = ["read", "write", "admin"]

​
LLM Completion Settings

Configure the model used for generating text:

# Ollama (local) configuration
[completion]
provider = "ollama"
model_name = "llama3.2-vision"
default_max_tokens = "1000"
default_temperature = 0.7
base_url = "http://localhost:11434"

# OpenAI configuration
[completion]
provider = "openai"
model_name = "gpt-4o"
default_max_tokens = "1000"
default_temperature = 0.7

​
Custom OpenAI Base URL

Morphik supports a global setting to customize the OpenAI API endpoint:

# OpenAI configuration
openai_base_url = "https://api.openai.com/v1"  # Override the base URL for all OpenAI API calls

This setting applies to all OpenAI services, enabling:

  • Integration with Azure OpenAI Service
  • Using OpenAI-compatible API providers
  • Working with corporate proxies
  • Using different regional endpoints

For Azure OpenAI:

openai_base_url = "https://{your-resource-name}.openai.azure.com/openai/deployments/{deployment-name}"

​
Database Connection

Choose your document metadata database:

[database]
provider = "postgres"

# Or for MongoDB
[database]
provider = "mongodb"
database_name = "databridge"
collection_name = "documents"

​
Embedding Configuration

Configure vector embeddings generation:

# Local embeddings with Ollama
[embedding]
provider = "ollama"
model_name = "nomic-embed-text"
dimensions = 768
similarity_metric = "cosine"
base_url = "http://localhost:11434"

# OpenAI embeddings
[embedding]
provider = "openai"
model_name = "text-embedding-3-small"
dimensions = 1536
similarity_metric = "dotProduct"

​
Document Parsing

Control how documents are processed and chunked:

[parser]
chunk_size = 1000        # Characters per chunk
chunk_overlap = 200      # Overlap between chunks
use_unstructured_api = false
use_contextual_chunking = false

​
Vision Processing

Configure multimodal processing for images and videos:

[parser.vision]
provider = "ollama"      # or "openai"
model_name = "llama3.2-vision"  # or "gpt-4o-mini"
frame_sample_rate = -1   # Set to -1 to disable frame captioning
base_url = "http://localhost:11434"  # Only for Ollama

​
Reranking

Configure the cross-encoder reranker for improved retrieval:

# Enable reranking
[reranker]
use_reranker = true
provider = "flag"
model_name = "BAAI/bge-reranker-large"
query_max_length = 256
passage_max_length = 512
use_fp16 = true
device = "mps"  # "cpu", "cuda", or "mps"

# Disable reranking
[reranker]
use_reranker = false

​
Document Storage

Choose where to store your document files:

# Local storage
[storage]
provider = "local"
storage_path = "./storage"

# AWS S3 storage
[storage]
provider = "aws-s3"
region = "us-east-2"
bucket_name = "databridge-storage"

​
Vector Database

Configure where vector embeddings are stored:

# PostgreSQL with pgvector
[vector_store]
provider = "pgvector"

# MongoDB Atlas
[vector_store]
provider = "mongodb"
database_name = "databridge"
collection_name = "document_chunks"

​
Rules Engine

Configure document processing with rules:

[rules]
provider = "ollama"    # or "openai"
model_name = "llama3.2"  # or "gpt-4o"
batch_size = 4096

​
Knowledge Graph

Configure entity extraction and graph building:

[graph]
provider = "ollama"    # or "openai"
model_name = "llama3.2"  # or "gpt-4o-mini"

​
General DataBridge Settings

Control core platform features:

[databridge]
enable_colpali = true    # Enable advanced retrieval
mode = "self_hosted"     # "cloud" or "self_hosted"

​
Telemetry

Configure observability settings:

[telemetry]
enabled = true
honeycomb_enabled = true
honeycomb_endpoint = "https://api.honeycomb.io"
honeycomb_proxy_endpoint = "https://otel-proxy.onrender.com"
service_name = "databridge-core"
otlp_timeout = 10
otlp_max_retries = 3
otlp_retry_delay = 1
otlp_max_export_batch_size = 512
otlp_schedule_delay_millis = 5000
otlp_max_queue_size = 2048

​
Environment Variables

Morphik uses environment variables for sensitive credentials and configuration that shouldn’t be stored in the configuration file:

  • OPENAI_API_KEY: Your OpenAI API key
  • JWT_SECRET_KEY: Secret for authentication tokens
  • POSTGRES_URI: PostgreSQL connection string
  • MONGODB_URI: MongoDB connection string
  • AWS_ACCESS_KEY and AWS_SECRET_ACCESS_KEY: For S3 storage
  • ASSEMBLYAI_API_KEY: For video transcription
  • ANTHROPIC_API_KEY: For contextual chunking (optional)
  • UNSTRUCTURED_API_KEY: For enhanced document parsing (optional)
  • HONEYCOMB_API_KEY: For telemetry (optional)

​
Complete Configuration Example

Here’s a complete example showing the structure of a databridge.toml file:

[api]
host = "localhost"  # Use "0.0.0.0" for Docker
port = 8000
reload = true

[auth]
jwt_algorithm = "HS256"
dev_mode = true
dev_entity_id = "dev_user"
dev_entity_type = "developer"
dev_permissions = ["read", "write", "admin"]

[completion]
provider = "ollama"  # or "openai"
model_name = "llama3.2-vision"
default_max_tokens = "1000"
default_temperature = 0.7
base_url = "http://localhost:11434"  # Only for Ollama

[database]
provider = "postgres"  # or "mongodb"

[embedding]
provider = "ollama"  # or "openai"
model_name = "nomic-embed-text"
dimensions = 768
similarity_metric = "cosine"
base_url = "http://localhost:11434"  # Only for Ollama

[parser]
chunk_size = 1000
chunk_overlap = 200
use_unstructured_api = false
use_contextual_chunking = false

[parser.vision]
provider = "ollama"  # or "openai"
model_name = "llama3.2-vision"
frame_sample_rate = -1
base_url = "http://localhost:11434"  # Only for Ollama

[reranker]
use_reranker = true
provider = "flag"
model_name = "BAAI/bge-reranker-large"
query_max_length = 256
passage_max_length = 512
use_fp16 = true
device = "mps"  # "cpu", "cuda", or "mps"

[storage]
provider = "local"  # or "aws-s3"
storage_path = "./storage"

[vector_store]
provider = "pgvector"  # or "mongodb"

[rules]
provider = "ollama"  # or "openai"
model_name = "llama3.2"
batch_size = 4096

[databridge]
enable_colpali = true
mode = "self_hosted"  # "cloud" or "self_hosted"

[graph]
provider = "ollama"  # or "openai"
model_name = "llama3.2"

[telemetry]
enabled = true
honeycomb_enabled = true
honeycomb_endpoint = "https://api.honeycomb.io"
honeycomb_proxy_endpoint = "https://otel-proxy.onrender.com"
service_name = "databridge-core"

​
Docker Configuration Adjustments

When using Docker, make these changes:

  1. Set host = "0.0.0.0" in the [api] section
  2. For Ollama integration, use base_url = "http://ollama:11434"
  3. Use container names in your database connection strings

For more details on Docker deployment, check out the DOCKER.md file in the repository.

​
Need Help?

If you’re having trouble with your configuration:

  1. Check the logs for error messages
  2. Run python quick_setup.py for guided setup
  3. Join our Discord community
  4. Open an issue on our GitHub repository