All Integrations

LangChain Integration

FoxNoseRetriever — a LangChain BaseRetriever backed by FoxNose Flux search. Drop it into any RAG chain for text, vector, or hybrid retrieval.

langchain-foxnoseGitHubDocumentation
Version:LatestLicense:Apache 2.0

Overview

langchain-foxnose provides FoxNoseRetriever, a LangChain BaseRetriever that connects to the FoxNose Flux search API. Use it as a drop-in retriever in any LangChain chain — RetrievalQA, ConversationalRetrievalChain, or your own custom pipeline.

Features

  • 4 search modes — text, vector, hybrid, and vector-boosted retrieval
  • Content mapping — single field, multiple fields, or a custom mapper function to build Document.page_content
  • Metadata control — whitelist, blacklist, or toggle system metadata on returned documents
  • Async support — native async retrieval via AsyncFluxClient
  • Structured filtering — pass a where parameter to filter results before ranking
  • Convenience constructor — FoxNoseRetriever.from_client_params() to create a retriever without manually instantiating a client

Installation

pip install langchain-foxnose

Quick Start

from langchain_foxnose import FoxNoseRetriever

retriever = FoxNoseRetriever.from_client_params(
    base_url="https://7c9h4pwu.fxns.io",
    api_prefix="content",
    public_key="YOUR_PUBLIC_KEY",
    secret_key="YOUR_SECRET_KEY",
    folder="articles",
    search_mode="hybrid",
    content_field="body",
)

docs = retriever.invoke("how to build AI applications")
for doc in docs:
    print(doc.page_content[:200])

Usage Examples

Vector search

retriever = FoxNoseRetriever.from_client_params(
    base_url="https://7c9h4pwu.fxns.io",
    api_prefix="content",
    public_key="YOUR_PUBLIC_KEY",
    secret_key="YOUR_SECRET_KEY",
    folder="articles",
    search_mode="vector",
    content_field="body",
    top_k=5,
    similarity_threshold=0.7,
)

docs = retriever.invoke("latest developments in machine learning")

Hybrid search with custom weights

retriever = FoxNoseRetriever.from_client_params(
    base_url="https://7c9h4pwu.fxns.io",
    api_prefix="content",
    public_key="YOUR_PUBLIC_KEY",
    secret_key="YOUR_SECRET_KEY",
    folder="articles",
    search_mode="hybrid",
    content_field="body",
    text_search_weight=0.3,
    vector_search_weight=0.7,
)

docs = retriever.invoke("quantum computing breakthroughs")

Filtered retrieval

retriever = FoxNoseRetriever.from_client_params(
    base_url="https://7c9h4pwu.fxns.io",
    api_prefix="content",
    public_key="YOUR_PUBLIC_KEY",
    secret_key="YOUR_SECRET_KEY",
    folder="articles",
    search_mode="hybrid",
    content_field="body",
    where={
        "$": {
            "all_of": [
                {"status__eq": "published"},
                {"category__in": ["tech", "science"]},
            ]
        }
    },
)

docs = retriever.invoke("renewable energy")

RetrievalQA chain

from langchain_openai import ChatOpenAI
from langchain.chains import RetrievalQA
from langchain_foxnose import FoxNoseRetriever

retriever = FoxNoseRetriever.from_client_params(
    base_url="https://7c9h4pwu.fxns.io",
    api_prefix="content",
    public_key="YOUR_PUBLIC_KEY",
    secret_key="YOUR_SECRET_KEY",
    folder="articles",
    search_mode="hybrid",
    content_field="body",
)

qa = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(model="gpt-4o"),
    retriever=retriever,
)

answer = qa.invoke("What are the best practices for API design?")
print(answer["result"])

Resources

Was this page helpful?