import numpy as np
from fastembed import TextEmbedding
from typing import List

# Example list of documents
documents: List[str] = [
    "This is built to be faster and lighter than other embedding libraries e.g. Transformers, Sentence-Transformers, etc.",
    "fastembed is supported by and maintained by Qdrant.",
]

# This will trigger the model download and initialization
embedding_model = TextEmbedding()
print("The model BAAI/bge-small-en-v1.5 is ready to use.")

embeddings_generator = embedding_model.embed(documents)  # reminder this is a generator
embeddings_list = list(embedding_model.embed(documents))
  # you can also convert the generator to a list, and that to a numpy array
len(embeddings_list[0]) # Vector of 384 dimensions

from qdrant_client import QdrantClient

# Initialize the client
client = QdrantClient("localhost", port=6333) # For production
# client = QdrantClient(":memory:") # For small experiments

# Prepare your documents, metadata, and IDs
docs = ["Qdrant has Langchain integrations", "Qdrant also has Llama Index integrations"]
metadata = [
    {"source": "Langchain-docs"},
    {"source": "Llama-index-docs"},
]
ids = [42, 2]

# If you want to change the model:
# client.set_model("sentence-transformers/all-MiniLM-L6-v2")
# List of supported models: https://qdrant.github.io/fastembed/examples/Supported_Models

# Use the new add() instead of upsert()
# This internally calls embed() of the configured embedding model
client.add(
    collection_name="demo_collection",
    documents=docs,
    metadata=metadata,
    ids=ids
)

search_result = client.query(
    collection_name="demo_collection",
    query_text="This is a query document"
)
print(search_result)