The headless CMS
with built-in search and AI

// Create a "products" collection via Management API or Dashboard
// Then define fields on a schema version:
{
  "title":       { "type": "string", "localizable": true },
  "description": { "type": "text", "vectorizable": true },
  "price":       { "type": "number" },
  "category":    { "type": "string", "enum": ["electronics", "clothing", "home"] },
  "published":   { "type": "boolean" }
}

// Management API
POST /v1/products

{
  "title": { "en": "Insulated Winter Parka" },
  "description": { "en": "Warm, waterproof jacket for extreme cold..." },
  "price": 189.00,
  "category": "clothing",
  "published": true
}
// → Stored + full-text indexed + vector embedded

// Flux API
POST /v1/products/_search

{
  "vector_search": { "query": "warm winter jacket" },
  "where": {
    "$": {
      "all_of": [
        { "category__eq": "clothing" },
        { "price__lte": 200 },
        { "published__eq": true }
      ]
    }
  }
}
// → Finds "Insulated Winter Parka" via semantic match
// → Even though "warm winter jacket" ≠ "insulated parka"

pip install langchain-foxnose langchain-openai

from langchain_foxnose import FoxNoseRetriever

retriever = FoxNoseRetriever.from_client_params(
    base_url="https://your-env.fxns.io",
    api_prefix="content",
    public_key="YOUR_PUBLIC_KEY",
    secret_key="YOUR_SECRET_KEY",
    folder="products",
    search_mode="hybrid",
    content_field="description",
)

from langchain_openai import ChatOpenAI
from langchain.chains import RetrievalQA

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

answer = qa.invoke("What winter jackets do you have under $200?")
print(answer["result"])
# → "We have the Insulated Winter Parka at $189..."