Bases vectorielles pour la récupération

from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import SentenceTransformerEmbeddings
import os

def main():
    # Define a path for ChromaDB to store data locally
    # This creates a 'chroma_db' folder if it doesn't exist
    persist_directory = "./chroma_db"
    
    # Initialize a local embedding function
    # 'all-MiniLM-L6-v2' is a small, efficient model
    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
    
    # Initialize ChromaDB. It will load if exists, or create new.
    vectordb = Chroma(
        persist_directory=persist_directory,
        embedding_function=embeddings
    )
    
    print("ChromaDB initialized successfully!")
    print(f"Database will persist at: {os.path.abspath(persist_directory)}")

if __name__ == "__main__":
    main()

from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import SentenceTransformerEmbeddings
from langchain_core.documents import Document
import os

def main():
    persist_directory = "./chroma_db"
    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
    
    # Load the existing ChromaDB or create a new one
    vectordb = Chroma(
        persist_directory=persist_directory,
        embedding_function=embeddings
    )
    
    # Example documents to add
    documents = [
        Document(page_content="The quick brown fox jumps over the lazy dog."),
        Document(page_content="Artificial intelligence is transforming industries."),
        Document(page_content="Machine learning is a subset of AI."),
        Document(page_content="Dogs are known for their loyalty and companionship.")
    ]
    
    print(f"Adding {len(documents)} documents to ChromaDB...")
    # add_documents handles embedding and storing
    vectordb.add_documents(documents)
    print("Documents added.")

if __name__ == "__main__":
    main()

from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import SentenceTransformerEmbeddings
import os

def main():
    persist_directory = "./chroma_db"
    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
    
    # Load the existing ChromaDB
    vectordb = Chroma(
        persist_directory=persist_directory,
        embedding_function=embeddings
    )
    
    query = "What is AI?"
    print(f"Searching for documents similar to: '{query}'")
    
    # Perform similarity search, retrieve top 2 results
    docs = vectordb.similarity_search(query, k=2)
    
    print("\nFound relevant documents:")
    for i, doc in enumerate(docs):
        print(f"--- Document {i+1} ---")
        print(doc.page_content)

if __name__ == "__main__":
    main()

from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import SentenceTransformerEmbeddings
import os

def main():
    persist_directory = "./chroma_db"
    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
    
    # Load the existing ChromaDB
    vectordb = Chroma(
        persist_directory=persist_directory,
        embedding_function=embeddings
    )
    
    # Convert the vector store into a retriever
    # search_kwargs allows passing arguments like 'k' to the underlying search
    retriever = vectordb.as_retriever(search_kwargs={"k": 2})
    
    query = "Tell me about AI."
    print(f"Using retriever to find documents for: '{query}'")
    
    # Use the retriever to get relevant documents
    relevant_docs = retriever.get_relevant_documents(query)
    
    print("\nRelevant documents retrieved by the retriever:")
    for i, doc in enumerate(relevant_docs):
        print(f"--- Retrieved Document {i+1} ---")
        print(doc.page_content)

if __name__ == "__main__":
    main()