Configuration File

Configuration

OpenViking uses a JSON configuration file (ov.conf) for settings.

Configuration File

Create ov.conf in your project directory:

{
  "embedding": {
    "dense": {
      "provider": "volcengine",
      "api_key": "your-api-key",
      "model": "doubao-embedding-vision-250615",
      "dimension": 1024
    }
  },
  "vlm": {
    "provider": "volcengine",
    "api_key": "your-api-key",
    "model": "doubao-seed-1-8-251228"
  },
  "rerank": {
    "provider": "volcengine",
    "api_key": "your-api-key",
    "model": "doubao-rerank-250615"
  },
  "storage": {
    "agfs": {
      "backend": "local",
      "path": "./data"
    },
    "vectordb": {
      "backend": "local",
      "path": "./data"
    }
  }
}

Configuration Sections

embedding

Embedding model configuration for vector search.

{
  "embedding": {
    "dense": {
      "provider": "volcengine",
      "api_key": "your-api-key",
      "model": "doubao-embedding-vision-250615",
      "dimension": 1024,
      "input": "multimodal"
    }
  }
}

See Embedding Configuration for details.

vlm

Vision Language Model for semantic extraction.

{
  "vlm": {
    "api_key": "your-api-key",
    "model": "doubao-seed-1-8-251228",
    "base_url": "https://ark.cn-beijing.volces.com/api/v3"
  }
}

See LLM Configuration for details.

rerank

Reranking model for search refinement.

{
  "rerank": {
    "provider": "volcengine",
    "api_key": "your-api-key",
    "model": "doubao-rerank-250615"
  }
}

storage

Storage backend configuration.

{
  "storage": {
    "agfs": {
      "backend": "local",
      "path": "./data",
      "timeout": 30.0
    },
    "vectordb": {
      "backend": "local",
      "path": "./data"
    }
  }
}

Environment Variables

Configuration values can be set via environment variables:

export VOLCENGINE_API_KEY="your-api-key"
export OPENVIKING_DATA_PATH="./data"

Configuration Priority

1. Constructor parameters (highest)
2. Config object
3. Configuration file (ov.conf)
4. Environment variables
5. Default values (lowest)

Programmatic Configuration

from openviking.utils.config import (
    OpenVikingConfig,
    StorageConfig,
    AGFSConfig,
    VectorDBBackendConfig,
    EmbeddingConfig,
    DenseEmbeddingConfig
)

config = OpenVikingConfig(
    storage=StorageConfig(
        agfs=AGFSConfig(
            backend="local",
            path="./custom_data",
        ),
        vectordb=VectorDBBackendConfig(
            backend="local",
            path="./custom_data",
        )
    ),
    embedding=EmbeddingConfig(
        dense=DenseEmbeddingConfig(
            provider="volcengine",
            api_key="your-api-key",
            model="doubao-embedding-vision-250615",
            dimension=1024
        )
    )
)

client = ov.AsyncOpenViking(config=config)

Configuration Reference

Full Schema

{
  "embedding": {
    "dense": {
      "provider": "volcengine",
      "api_key": "string",
      "model": "string",
      "dimension": 1024,
      "input": "multimodal"
    }
  },
  "vlm": {
    "provider": "string",
    "api_key": "string",
    "model": "string",
    "base_url": "string"
  },
  "rerank": {
    "provider": "volcengine",
    "api_key": "string",
    "model": "string"
  },
  "storage": {
    "agfs": {
      "backend": "local|remote",
      "path": "string",
      "url": "string",
      "timeout": 30.0
    },
    "vectordb": {
      "backend": "local|remote",
      "path": "string",
      "url": "string"
    }
  },
  "user": "string"
}

Related Documentation

• Embedding Configuration - Embedding setup
• LLM Configuration - LLM setup
• Client - Client initialization