app.py

from fastapi import FastAPI
from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient
from qdrant_client.http.models import Distance, VectorParams

from langchain_qdrant import FastEmbedSparse, QdrantVectorStore, RetrievalMode
from qdrant_client import QdrantClient, models
from qdrant_client.http.models import Distance, SparseVectorParams, VectorParams

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees Fahrenheit.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

docs = documents

sparse_embeddings = FastEmbedSparse(model_name="Qdrant/bm25")

client = QdrantClient(path="tmp/langchain_qdrant")

# Create a collection with sparse vectors
client.create_collection(
    collection_name="my_documents",
    vectors_config={"dense": VectorParams(size=3072, distance=Distance.COSINE)},
    sparse_vectors_config={
        "sparse": SparseVectorParams(index=models.SparseIndexParams(on_disk=False))
    },
)

qdrant = QdrantVectorStore(
    client=client,
    collection_name="my_documents",
    sparse_embedding=sparse_embeddings,
    retrieval_mode=RetrievalMode.SPARSE,
    sparse_vector_name="sparse",
    
)

qdrant.add_documents(documents=documents, ids=uuids)

app = FastAPI()

@app.get("/get_data")
def get_data(query: str):
    # query = "How much money did the robbers steal?"
    found_docs = [x.model_dump() for x in qdrant.similarity_search(query)]

    for doc in found_docs:
        doc.pop("id", None)
        # key = 
        for k in list(doc["metadata"].keys()):
            if k[0] == "_":
                doc["metadata"].pop(k)

    return {
        "data": found_docs
    }


@app.get("/")
def greet_json():
    return {"Hello": "World!"}