Chroma

import chromadb
# Create clientclient = chromadb.Client()
# Create collectioncollection = client.create_collection(name="my_collection")
# Add documentscollection.add(    documents=["This is document 1", "This is document 2"],    metadatas=[{"source": "doc1"}, {"source": "doc2"}],    ids=["id1", "id2"])
# Queryresults = collection.query(    query_texts=["document about topic"],    n_results=2)
print(results)

# Simple collectioncollection = client.create_collection("my_docs")
# With custom embedding functionfrom chromadb.utils import embedding_functions
openai_ef = embedding_functions.OpenAIEmbeddingFunction(    api_key="your-key",    model_name="text-embedding-3-small")
collection = client.create_collection(    name="my_docs",    embedding_function=openai_ef)
# Get existing collectioncollection = client.get_collection("my_docs")
# Delete collectionclient.delete_collection("my_docs")

# Add with auto-generated IDscollection.add(    documents=["Doc 1", "Doc 2", "Doc 3"],    metadatas=[        {"source": "web", "category": "tutorial"},        {"source": "pdf", "page": 5},        {"source": "api", "timestamp": "2025-01-01"}    ],    ids=["id1", "id2", "id3"])
# Add with custom embeddingscollection.add(    embeddings=[[0.1, 0.2, ...], [0.3, 0.4, ...]],    documents=["Doc 1", "Doc 2"],    ids=["id1", "id2"])

# Basic queryresults = collection.query(    query_texts=["machine learning tutorial"],    n_results=5)
# Query with filtersresults = collection.query(    query_texts=["Python programming"],    n_results=3,    where={"source": "web"})
# Query with metadata filtersresults = collection.query(    query_texts=["advanced topics"],    where={        "$and": [            {"category": "tutorial"},            {"difficulty": {"$gte": 3}}        ]    })
# Access resultsprint(results["documents"])      # List of matching documentsprint(results["metadatas"])      # Metadata for each docprint(results["distances"])      # Similarity scoresprint(results["ids"])            # Document IDs

# Get by IDsdocs = collection.get(    ids=["id1", "id2"])
# Get with filtersdocs = collection.get(    where={"category": "tutorial"},    limit=10)
# Get all documentsdocs = collection.get()

# Update document contentcollection.update(    ids=["id1"],    documents=["Updated content"],    metadatas=[{"source": "updated"}])

# Delete by IDscollection.delete(ids=["id1", "id2"])
# Delete with filtercollection.delete(    where={"source": "outdated"})

# Persist to diskclient = chromadb.PersistentClient(path="./chroma_db")
collection = client.create_collection("my_docs")collection.add(documents=["Doc 1"], ids=["id1"])
# Data persisted automatically# Reload later with same pathclient = chromadb.PersistentClient(path="./chroma_db")collection = client.get_collection("my_docs")

# Uses sentence-transformers by defaultcollection = client.create_collection("my_docs")# Default model: all-MiniLM-L6-v2

from chromadb.utils import embedding_functions
openai_ef = embedding_functions.OpenAIEmbeddingFunction(    api_key="your-key",    model_name="text-embedding-3-small")
collection = client.create_collection(    name="openai_docs",    embedding_function=openai_ef)

huggingface_ef = embedding_functions.HuggingFaceEmbeddingFunction(    api_key="your-key",    model_name="sentence-transformers/all-mpnet-base-v2")
collection = client.create_collection(    name="hf_docs",    embedding_function=huggingface_ef)

from chromadb import Documents, EmbeddingFunction, Embeddings
class MyEmbeddingFunction(EmbeddingFunction):    def __call__(self, input: Documents) -> Embeddings:        # Your embedding logic        return embeddings
my_ef = MyEmbeddingFunction()collection = client.create_collection(    name="custom_docs",    embedding_function=my_ef)

# Exact matchresults = collection.query(    query_texts=["query"],    where={"category": "tutorial"})
# Comparison operatorsresults = collection.query(    query_texts=["query"],    where={"page": {"$gt": 10}}  # $gt, $gte, $lt, $lte, $ne)
# Logical operatorsresults = collection.query(    query_texts=["query"],    where={        "$and": [            {"category": "tutorial"},            {"difficulty": {"$lte": 3}}        ]    }  # Also: $or)
# Containsresults = collection.query(    query_texts=["query"],    where={"tags": {"$in": ["python", "ml"]}})

from langchain_chroma import Chromafrom langchain_openai import OpenAIEmbeddingsfrom langchain.text_splitter import RecursiveCharacterTextSplitter
# Split documentstext_splitter = RecursiveCharacterTextSplitter(chunk_size=1000)docs = text_splitter.split_documents(documents)
# Create Chroma vector storevectorstore = Chroma.from_documents(    documents=docs,    embedding=OpenAIEmbeddings(),    persist_directory="./chroma_db")
# Queryresults = vectorstore.similarity_search("machine learning", k=3)
# As retrieverretriever = vectorstore.as_retriever(search_kwargs={"k": 5})

from llama_index.vector_stores.chroma import ChromaVectorStorefrom llama_index.core import VectorStoreIndex, StorageContextimport chromadb
# Initialize Chromadb = chromadb.PersistentClient(path="./chroma_db")collection = db.get_or_create_collection("my_collection")
# Create vector storevector_store = ChromaVectorStore(chroma_collection=collection)storage_context = StorageContext.from_defaults(vector_store=vector_store)
# Create indexindex = VectorStoreIndex.from_documents(    documents,    storage_context=storage_context)
# Queryquery_engine = index.as_query_engine()response = query_engine.query("What is machine learning?")

# Run Chroma server# Terminal: chroma run --path ./chroma_db --port 8000
# Connect to serverimport chromadbfrom chromadb.config import Settings
client = chromadb.HttpClient(    host="localhost",    port=8000,    settings=Settings(anonymized_telemetry=False))
# Use as normalcollection = client.get_or_create_collection("my_docs")