LOTR (Merger Retriever)

Lord of the Retrievers, also known as MergerRetriever, takes a list of retrievers as input and merges the results of their get_relevant_documents() methods into a single list. The merged results will be a list of documents that are relevant to the query and that have been ranked by the different retrievers.

The MergerRetriever class can be used to improve the accuracy of document retrieval in a number of ways. First, it can combine the results of multiple retrievers, which can help to reduce the risk of bias in the results. Second, it can rank the results of the different retrievers, which can help to ensure that the most relevant documents are returned first.

import os
import chromadb
from langchain.retrievers.merger_retriever import MergerRetriever
from langchain.vectorstores import Chroma
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.embeddings import OpenAIEmbeddings
from langchain.document_transformers import EmbeddingsRedundantFilter
from langchain.retrievers.document_compressors import DocumentCompressorPipeline
from langchain.retrievers import ContextualCompressionRetriever

# Get 3 diff embeddings.
all_mini = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
multi_qa_mini = HuggingFaceEmbeddings(model_name="multi-qa-MiniLM-L6-dot-v1")
filter_embeddings = OpenAIEmbeddings()

ABS_PATH = os.path.dirname(os.path.abspath(__file__))
DB_DIR = os.path.join(ABS_PATH, "db")

# Instantiate 2 diff cromadb indexs, each one with a diff embedding.
client_settings = chromadb.config.Settings(
    chroma_db_impl="duckdb+parquet",
    persist_directory=DB_DIR,
    anonymized_telemetry=False,
)
db_all = Chroma(
    collection_name="project_store_all",
    persist_directory=DB_DIR,
    client_settings=client_settings,
    embedding_function=all_mini,
)
db_multi_qa = Chroma(
    collection_name="project_store_multi",
    persist_directory=DB_DIR,
    client_settings=client_settings,
    embedding_function=multi_qa_mini,
)

# Define 2 diff retrievers with 2 diff embeddings and diff search type.
retriever_all = db_all.as_retriever(
    search_type="similarity", search_kwargs={"k": 5, "include_metadata": True}
)
retriever_multi_qa = db_multi_qa.as_retriever(
    search_type="mmr", search_kwargs={"k": 5, "include_metadata": True}
)

# The Lord of the Retrievers will hold the ouput of boths retrievers and can be used as any other
# retriever on different types of chains.
lotr = MergerRetriever(retrievers=[retriever_all, retriever_multi_qa])

Remove redundant results from the merged retrievers.

# We can remove redundant results from both retrievers using yet another embedding.
# Using multiples embeddings in diff steps could help reduce biases.
filter = EmbeddingsRedundantFilter(embeddings=filter_embeddings)
pipeline = DocumentCompressorPipeline(transformers=[filter])
compression_retriever = ContextualCompressionRetriever(
    base_compressor=pipeline, base_retriever=lotr
)