import logging from typing import Dict, List, Optional from pydantic import BaseModel try: import chromadb from chromadb.config import Settings except ImportError: raise ImportError("The 'chromadb' library is required. Please install it using 'pip install chromadb'.") from mem0.vector_stores.base import VectorStoreBase logger = logging.getLogger(__name__) class OutputData(BaseModel): id: Optional[str] # memory id score: Optional[float] # distance payload: Optional[Dict] # metadata class ChromaDB(VectorStoreBase): def __init__( self, collection_name: str, client: Optional[chromadb.Client] = None, host: Optional[str] = None, port: Optional[int] = None, path: Optional[str] = None, ): """ Initialize the Chromadb vector store. Args: collection_name (str): Name of the collection. client (chromadb.Client, optional): Existing chromadb client instance. Defaults to None. host (str, optional): Host address for chromadb server. Defaults to None. port (int, optional): Port for chromadb server. Defaults to None. path (str, optional): Path for local chromadb database. Defaults to None. """ if client: self.client = client else: self.settings = Settings(anonymized_telemetry=False) if host and port: self.settings.chroma_server_host = host self.settings.chroma_server_http_port = port self.settings.chroma_api_impl = "chromadb.api.fastapi.FastAPI" else: if path is None: path = "db" self.settings.persist_directory = path self.settings.is_persistent = True self.client = chromadb.Client(self.settings) self.collection_name = collection_name self.collection = self.create_col(collection_name) def _parse_output(self, data: Dict) -> List[OutputData]: """ Parse the output data. Args: data (Dict): Output data. Returns: List[OutputData]: Parsed output data. """ keys = ["ids", "distances", "metadatas"] values = [] for key in keys: value = data.get(key, []) if isinstance(value, list) and value and isinstance(value[0], list): value = value[0] values.append(value) ids, distances, metadatas = values max_length = max(len(v) for v in values if isinstance(v, list) and v is not None) result = [] for i in range(max_length): entry = OutputData( id=ids[i] if isinstance(ids, list) and ids and i < len(ids) else None, score=(distances[i] if isinstance(distances, list) and distances and i < len(distances) else None), payload=(metadatas[i] if isinstance(metadatas, list) and metadatas and i < len(metadatas) else None), ) result.append(entry) return result def create_col(self, name: str, embedding_fn: Optional[callable] = None): """ Create a new collection. Args: name (str): Name of the collection. embedding_fn (Optional[callable]): Embedding function to use. Defaults to None. Returns: chromadb.Collection: The created or retrieved collection. """ # Skip creating collection if already exists collections = self.list_cols() for collection in collections: if collection.name == name: logging.debug(f"Collection {name} already exists. Skipping creation.") collection = self.client.get_or_create_collection( name=name, embedding_function=embedding_fn, ) return collection def insert( self, vectors: List[list], payloads: Optional[List[Dict]] = None, ids: Optional[List[str]] = None, ): """ Insert vectors into a collection. Args: vectors (List[list]): List of vectors to insert. payloads (Optional[List[Dict]], optional): List of payloads corresponding to vectors. Defaults to None. ids (Optional[List[str]], optional): List of IDs corresponding to vectors. Defaults to None. """ logger.info(f"Inserting {len(vectors)} vectors into collection {self.collection_name}") self.collection.add(ids=ids, embeddings=vectors, metadatas=payloads) def search(self, query: List[list], limit: int = 5, filters: Optional[Dict] = None) -> List[OutputData]: """ Search for similar vectors. Args: query (List[list]): Query vector. limit (int, optional): Number of results to return. Defaults to 5. filters (Optional[Dict], optional): Filters to apply to the search. Defaults to None. Returns: List[OutputData]: Search results. """ results = self.collection.query(query_embeddings=query, where=filters, n_results=limit) final_results = self._parse_output(results) return final_results def delete(self, vector_id: str): """ Delete a vector by ID. Args: vector_id (str): ID of the vector to delete. """ self.collection.delete(ids=vector_id) def update( self, vector_id: str, vector: Optional[List[float]] = None, payload: Optional[Dict] = None, ): """ Update a vector and its payload. Args: vector_id (str): ID of the vector to update. vector (Optional[List[float]], optional): Updated vector. Defaults to None. payload (Optional[Dict], optional): Updated payload. Defaults to None. """ self.collection.update(ids=vector_id, embeddings=vector, metadatas=payload) def get(self, vector_id: str) -> OutputData: """ Retrieve a vector by ID. Args: vector_id (str): ID of the vector to retrieve. Returns: OutputData: Retrieved vector. """ result = self.collection.get(ids=[vector_id]) return self._parse_output(result)[0] def list_cols(self) -> List[chromadb.Collection]: """ List all collections. Returns: List[chromadb.Collection]: List of collections. """ return self.client.list_collections() def delete_col(self): """ Delete a collection. """ self.client.delete_collection(name=self.collection_name) def col_info(self) -> Dict: """ Get information about a collection. Returns: Dict: Collection information. """ return self.client.get_collection(name=self.collection_name) def list(self, filters: Optional[Dict] = None, limit: int = 100) -> List[OutputData]: """ List all vectors in a collection. Args: filters (Optional[Dict], optional): Filters to apply to the list. Defaults to None. limit (int, optional): Number of vectors to return. Defaults to 100. Returns: List[OutputData]: List of vectors. """ results = self.collection.get(where=filters, limit=limit) return [self._parse_output(results)]