LlamaIndex integration

pip install chromadb llama-index llama-index-vector-stores-chroma

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, StorageContext
from llama_index.vector_stores.chroma import ChromaVectorStore
import chromadb

# Load documents
documents = SimpleDirectoryReader("./data").load_data()

# Create Chroma client and collection
chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")

# Create vector store
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

# Build index
index = VectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context
)

# Query the index
query_engine = index.as_query_engine()
response = query_engine.query("What is this document about?")
print(response)

import chromadb
from llama_index.vector_stores.chroma import ChromaVectorStore

# Create persistent client
chroma_client = chromadb.PersistentClient(path="./chroma_db")

# Get or create collection
chroma_collection = chroma_client.get_or_create_collection("my_collection")

# Create vector store
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)

import chromadb
from chromadb.config import Settings

# Connect to remote Chroma server
chroma_client = chromadb.HttpClient(
    host="localhost",
    port=8000,
    settings=Settings(allow_reset=True, anonymized_telemetry=False)
)

chroma_collection = chroma_client.get_or_create_collection("my_collection")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)

from llama_index.core.vector_stores import MetadataFilters, ExactMatchFilter

# Query with metadata filters
filters = MetadataFilters(
    filters=[ExactMatchFilter(key="source", value="documentation")]
)

query_engine = index.as_query_engine(filters=filters)
response = query_engine.query("Your question")

from llama_index.core.retrievers import VectorIndexRetriever

# Create custom retriever
retriever = VectorIndexRetriever(
    index=index,
    similarity_top_k=5,
)

# Retrieve nodes
nodes = retriever.retrieve("query text")

import chromadb
from llama_index.core import VectorStoreIndex
from llama_index.vector_stores.chroma import ChromaVectorStore

# Connect to existing collection
chroma_client = chromadb.PersistentClient(path="./chroma_db")
chroma_collection = chroma_client.get_collection("existing_collection")

# Load from vector store
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
index = VectorStoreIndex.from_vector_store(vector_store)