Pipeline

Create a RAG pipeline object on Embedchain. This is the main entrypoint for a developer to interact with Embedchain APIs. A pipeline configures the llm, vector database, embedding model, and retrieval strategy of your choice.

Attributes

local_id · str

Pipeline ID

name · str

Name of the pipeline

config · BaseConfig

Configuration of the pipeline

llm · BaseLlm

Configured LLM for the RAG pipeline

db · BaseVectorDB

Configured vector database for the RAG pipeline

embedding_model · BaseEmbedder

Configured embedding model for the RAG pipeline

chunker · ChunkerConfig

Chunker configuration

client · Client

Client object (used to deploy a pipeline to Embedchain platform)

logger · logging.Logger

Logger object

Usage

You can create an embedchain pipeline instance using the following methods:

Default setting

Code Example

from embedchain import App
app = App()

Python Dict

Code Example

from embedchain import App

config_dict = {
  'llm': {
    'provider': 'gpt4all',
    'config': {
      'model': 'orca-mini-3b-gguf2-q4_0.gguf',
      'temperature': 0.5,
      'max_tokens': 1000,
      'top_p': 1,
      'stream': False
    }
  },
  'embedder': {
    'provider': 'gpt4all'
  }
}

# load llm configuration from config dict
app = App.from_config(config=config_dict)

YAML Config

main.py

from embedchain import App

# load llm configuration from config.yaml file
app = App.from_config(config_path="config.yaml")

JSON Config

main.py

from embedchain import App

# load llm configuration from config.json file
app = App.from_config(config_path="config.json")