Default Configuration

During the example pipeline creation, a default config.json is loaded and passed to the pipeline. It provides settings for the following services:

• Embedding settings
• Vector Database provider
• LLM settings
• Parsing logic
• Evaluation provider
• and more

The default values for the config are shown below:

{
  "embedding": {
    "provider": "openai",
    "model": "text-embedding-ada-002",
    "dimension": 1536,
    "batch_size": 32,
    "text_splitter": {
      "type": "recursive_character",
      "chunk_size": 512,
      "chunk_overlap": 20
    }
  },
  "evals": {
    "provider": "deepeval",
    "sampling_fraction": 1.0
  },
  "language_model": {
    "provider": "litellm"
  },
  "logging_database": {
    "provider": "local",
    "collection_name": "demo_logs",
    "level": "INFO"
  },
  "ingestion": {
    "provider": "local"
  },
  "vector_database": {
    "provider": "local",
    "collection_name": "demo_vecs" 
  },
  "app": {
    "max_logs": 100,
    "max_file_size_in_mb": 100
  }
}

The available options for each section are:

• embedding:

  • provider: "openai", "sentence-transformers" (see Embedding Providers for more info)
  • model: embedding model to use (e.g., "text-embedding-ada-002" for OpenAI)
  • dimension: embedding dimension
  • batch_size: number of texts to embed in each batch

• evals:

  • provider: "deepeval", "parea" (see Evaluation Providers for more info)
  • sampling_fraction: sampling sampling_fraction for evaluation (e.g., 1.0 for 100% of requests)

• language_model:

  • provider: "litellm", "openai", "llama-cpp" (see LLM Providers for more info)

• logging_database:

  • provider: "local", "postgres", "redis"
  • collection_name: name of the collection to store logs
  • level: logging level (e.g., "INFO", "DEBUG")

• ingestion:

  • provider: "local"
  • text_splitter: configuration for text splitting
    • type: "recursive_character"
    • chunk_size: target chunk size in characters
    • chunk_overlap: number of overlapping characters between chunks

• vector_database:

  • provider: "local", "pgvector", "qdrant" (see Vector Database Providers for more info)
  • collection_name: name of the collection to store vector embeddings

• app:

  • max_logs: maximum number of logs to retrieve
  • max_file_size_in_mb: maximum file size allowed for ingestion (in MB)

For more detailed information on configuring specific providers, please refer to the relevant documentation:

• LLM Providers
• Vector Database Providers
• Embedding Providers
• Evaluation Providers

These documentation files provide in-depth guides on setting up and using each provider, including any required environment variables and additional configuration options.

To launch the default pipeline with your own config, you may run the following code:

class E2EPipelineFactory:
    ...
    app = E2EPipelineFactory.create_pipeline(
        # override with your own config.json
        config=R2RConfig.load_config("your_config_path.json"),
    )