langchain_community.vectorstores.chroma.Chroma

class langchain_community.vectorstores.chroma.Chroma(collection_name: str = 'langchain', embedding_function: Optional[Embeddings] = None, persist_directory: Optional[str] = None, client_settings: Optional[chromadb.config.Settings] = None, collection_metadata: Optional[Dict] = None, client: Optional[chromadb.Client] = None, relevance_score_fn: Optional[Callable[[float], float]] = None)

ChromaDB vector store.

To use, you should have the chromadb python package installed.

Example

from langchain_community.vectorstores import Chroma
from langchain_community.embeddings.openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()
vectorstore = Chroma("langchain_store", embeddings)

Initialize with a Chroma client.

Attributes

embeddings

Access the query embedding object if available.

Methods

__init__([collection_name, ...])	Initialize with a Chroma client.
aadd_documents(documents, **kwargs)	Run more documents through the embeddings and add to the vectorstore.
aadd_texts(texts[, metadatas])	Run more texts through the embeddings and add to the vectorstore.
add_documents(documents, **kwargs)	Run more documents through the embeddings and add to the vectorstore.
add_images(uris[, metadatas, ids])	Run more images through the embeddings and add to the vectorstore.
add_texts(texts[, metadatas, ids])	Run more texts through the embeddings and add to the vectorstore.
adelete([ids])	Delete by vector ID or other criteria.
afrom_documents(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
afrom_texts(texts, embedding[, metadatas])	Return VectorStore initialized from texts and embeddings.
amax_marginal_relevance_search(query[, k, ...])	Return docs selected using the maximal marginal relevance.
amax_marginal_relevance_search_by_vector(...)	Return docs selected using the maximal marginal relevance.
as_retriever(**kwargs)	Return VectorStoreRetriever initialized from this VectorStore.
asearch(query, search_type, **kwargs)	Return docs most similar to query using specified search type.
asimilarity_search(query[, k])	Return docs most similar to query.
asimilarity_search_by_vector(embedding[, k])	Return docs most similar to embedding vector.
asimilarity_search_with_relevance_scores(query)	Return docs and relevance scores in the range [0, 1], asynchronously.
asimilarity_search_with_score(*args, **kwargs)	Run similarity search with distance asynchronously.
delete([ids])	Delete by vector IDs.
delete_collection()	Delete the collection.
encode_image(uri)	Get base64 string from image URI.
from_documents(documents[, embedding, ids, ...])	Create a Chroma vectorstore from a list of documents.
from_texts(texts[, embedding, metadatas, ...])	Create a Chroma vectorstore from a raw documents.
get([ids, where, limit, offset, ...])	Gets the collection.
max_marginal_relevance_search(query[, k, ...])	Return docs selected using the maximal marginal relevance.
max_marginal_relevance_search_by_vector(...)	Return docs selected using the maximal marginal relevance.
persist()	Persist the collection.
search(query, search_type, **kwargs)	Return docs most similar to query using specified search type.
similarity_search(query[, k, filter])	Run similarity search with Chroma.
similarity_search_by_vector(embedding[, k, ...])	Return docs most similar to embedding vector.
similarity_search_by_vector_with_relevance_scores(...)	Return docs most similar to embedding vector and similarity score.
similarity_search_with_relevance_scores(query)	Return docs and relevance scores in the range [0, 1].
similarity_search_with_score(query[, k, ...])	Run similarity search with Chroma with distance.
update_document(document_id, document)	Update a document in the collection.
update_documents(ids, documents)	Update a document in the collection.

Parameters

• collection_name (str) –

• embedding_function (Optional[Embeddings]) –

• persist_directory (Optional[str]) –

• client_settings (Optional[chromadb.config.Settings]) –

• collection_metadata (Optional[Dict]) –

• client (Optional[chromadb.Client]) –

• relevance_score_fn (Optional[Callable[[float], float]]) –

__init__(collection_name: str = 'langchain', embedding_function: Optional[Embeddings] = None, persist_directory: Optional[str] = None, client_settings: Optional[chromadb.config.Settings] = None, collection_metadata: Optional[Dict] = None, client: Optional[chromadb.Client] = None, relevance_score_fn: Optional[Callable[[float], float]] = None) → None

Initialize with a Chroma client.

Parameters

• collection_name (str) –

• embedding_function (Optional[Embeddings]) –

• persist_directory (Optional[str]) –

• client_settings (Optional[chromadb.config.Settings]) –

• collection_metadata (Optional[Dict]) –

• client (Optional[chromadb.Client]) –

• relevance_score_fn (Optional[Callable[[float], float]]) –

Return type

None

async aadd_documents(documents: List[Document], **kwargs: Any) → List[str]

Run more documents through the embeddings and add to the vectorstore.

Parameters

• (List[Document] (documents) – Documents to add to the vectorstore.

• documents (List[Document]) –

• kwargs (Any) –

Returns

List of IDs of the added texts.

Return type

List[str]

async aadd_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any) → List[str]

Run more texts through the embeddings and add to the vectorstore.

Parameters

• texts (Iterable[str]) –

• metadatas (Optional[List[dict]]) –

• kwargs (Any) –

Return type

List[str]

add_documents(documents: List[Document], **kwargs: Any) → List[str]

Run more documents through the embeddings and add to the vectorstore.

Parameters

• (List[Document] (documents) – Documents to add to the vectorstore.

• documents (List[Document]) –

• kwargs (Any) –

Returns

List of IDs of the added texts.

Return type

List[str]

add_images(uris: List[str], metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, **kwargs: Any) → List[str]

Run more images through the embeddings and add to the vectorstore.

Parameters

• List[str] (uris) – File path to the image.

• metadatas (Optional[List[dict]], optional) – Optional list of metadatas.

• ids (Optional[List[str]], optional) – Optional list of IDs.

• uris (List[str]) –

• kwargs (Any) –

Returns

List of IDs of the added images.

Return type

List[str]

add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, **kwargs: Any) → List[str]

Run more texts through the embeddings and add to the vectorstore.

Parameters

• texts (Iterable[str]) – Texts to add to the vectorstore.

• metadatas (Optional[List[dict]], optional) – Optional list of metadatas.

• ids (Optional[List[str]], optional) – Optional list of IDs.

• kwargs (Any) –

Returns

List of IDs of the added texts.

Return type

List[str]

async adelete(ids: Optional[List[str]] = None, **kwargs: Any) → Optional[bool]

Delete by vector ID or other criteria.

Parameters

• ids (Optional[List[str]]) – List of ids to delete.

• **kwargs (Any) – Other keyword arguments that subclasses might use.

Returns

True if deletion is successful, False otherwise, None if not implemented.

Return type

Optional[bool]

async classmethod afrom_documents(documents: List[Document], embedding: Embeddings, **kwargs: Any) → VST

Return VectorStore initialized from documents and embeddings.

Parameters

• documents (List[Document]) –

• embedding (Embeddings) –

• kwargs (Any) –

Return type

VST

async classmethod afrom_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → VST

Return VectorStore initialized from texts and embeddings.

Parameters

• texts (List[str]) –

• embedding (Embeddings) –

• metadatas (Optional[List[dict]]) –

• kwargs (Any) –

Return type

VST

async amax_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

Parameters

• query (str) –

• k (int) –

• fetch_k (int) –

• lambda_mult (float) –

• kwargs (Any) –

Return type

List[Document]

async amax_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

Parameters

• embedding (List[float]) –

• k (int) –

• fetch_k (int) –

• lambda_mult (float) –

• kwargs (Any) –

Return type

List[Document]

as_retriever(**kwargs: Any) → VectorStoreRetriever

Return VectorStoreRetriever initialized from this VectorStore.

Parameters

• search_type (Optional[str]) – Defines the type of search that the Retriever should perform. Can be “similarity” (default), “mmr”, or “similarity_score_threshold”.

• search_kwargs (Optional[Dict]) –

  Keyword arguments to pass to the search function. Can include things like:

  k: Amount of documents to return (Default: 4) score_threshold: Minimum relevance threshold

  for similarity_score_threshold

  fetch_k: Amount of documents to pass to MMR algorithm (Default: 20) lambda_mult: Diversity of results returned by MMR;

  1 for minimum diversity and 0 for maximum. (Default: 0.5)

  filter: Filter by document metadata

• kwargs (Any) –

Returns

Retriever class for VectorStore.

Return type

VectorStoreRetriever

Examples:

# Retrieve more documents with higher diversity
# Useful if your dataset has many similar documents
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 6, 'lambda_mult': 0.25}
)

# Fetch more documents for the MMR algorithm to consider
# But only return the top 5
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 5, 'fetch_k': 50}
)

# Only retrieve documents that have a relevance score
# Above a certain threshold
docsearch.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={'score_threshold': 0.8}
)

# Only get the single most similar document from the dataset
docsearch.as_retriever(search_kwargs={'k': 1})

# Use a filter to only retrieve documents from a specific paper
docsearch.as_retriever(
    search_kwargs={'filter': {'paper_title':'GPT-4 Technical Report'}}
)

async asearch(query: str, search_type: str, **kwargs: Any) → List[Document]

Return docs most similar to query using specified search type.

Parameters

• query (str) –

• search_type (str) –

• kwargs (Any) –

Return type

List[Document]

async asimilarity_search(query: str, k: int = 4, **kwargs: Any) → List[Document]

Return docs most similar to query.

Parameters

• query (str) –

• k (int) –

• kwargs (Any) –

Return type

List[Document]

async asimilarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[Document]

Return docs most similar to embedding vector.

Parameters

• embedding (List[float]) –

• k (int) –

• kwargs (Any) –

Return type

List[Document]

async asimilarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → List[Tuple[Document, float]]

Return docs and relevance scores in the range [0, 1], asynchronously.

0 is dissimilar, 1 is most similar.

Parameters

• query (str) – input text

• k (int) – Number of Documents to return. Defaults to 4.

• **kwargs (Any) –

  kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

  filter the resulting set of retrieved docs

Returns

List of Tuples of (doc, similarity_score)

Return type

List[Tuple[Document, float]]

async asimilarity_search_with_score(*args: Any, **kwargs: Any) → List[Tuple[Document, float]]

Run similarity search with distance asynchronously.

Parameters

• args (Any) –

• kwargs (Any) –

Return type

List[Tuple[Document, float]]

delete(ids: Optional[List[str]] = None, **kwargs: Any) → None

Delete by vector IDs.

Parameters

• ids (Optional[List[str]]) – List of ids to delete.

• kwargs (Any) –

Return type

None

delete_collection() → None

Delete the collection.

Return type

None

encode_image(uri: str) → str

Get base64 string from image URI.

Parameters

uri (str) –

Return type

str

classmethod from_documents(documents: List[Document], embedding: Optional[Embeddings] = None, ids: Optional[List[str]] = None, collection_name: str = 'langchain', persist_directory: Optional[str] = None, client_settings: Optional[chromadb.config.Settings] = None, client: Optional[chromadb.Client] = None, collection_metadata: Optional[Dict] = None, **kwargs: Any) → Chroma

Create a Chroma vectorstore from a list of documents.

If a persist_directory is specified, the collection will be persisted there. Otherwise, the data will be ephemeral in-memory.

Parameters

• collection_name (str) – Name of the collection to create.

• persist_directory (Optional[str]) – Directory to persist the collection.

• ids (Optional[List[str]]) – List of document IDs. Defaults to None.

• documents (List[Document]) – List of documents to add to the vectorstore.

• embedding (Optional[Embeddings]) – Embedding function. Defaults to None.

• client_settings (Optional[chromadb.config.Settings]) – Chroma client settings

• collection_metadata (Optional[Dict]) – Collection configurations. Defaults to None.

• client (Optional[chromadb.Client]) –

• kwargs (Any) –

Returns

Chroma vectorstore.

Return type

Chroma

classmethod from_texts(texts: List[str], embedding: Optional[Embeddings] = None, metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, collection_name: str = 'langchain', persist_directory: Optional[str] = None, client_settings: Optional[chromadb.config.Settings] = None, client: Optional[chromadb.Client] = None, collection_metadata: Optional[Dict] = None, **kwargs: Any) → Chroma

Create a Chroma vectorstore from a raw documents.

If a persist_directory is specified, the collection will be persisted there. Otherwise, the data will be ephemeral in-memory.

Parameters

• texts (List[str]) – List of texts to add to the collection.

• collection_name (str) – Name of the collection to create.

• persist_directory (Optional[str]) – Directory to persist the collection.

• embedding (Optional[Embeddings]) – Embedding function. Defaults to None.

• metadatas (Optional[List[dict]]) – List of metadatas. Defaults to None.

• ids (Optional[List[str]]) – List of document IDs. Defaults to None.

• client_settings (Optional[chromadb.config.Settings]) – Chroma client settings

• collection_metadata (Optional[Dict]) – Collection configurations. Defaults to None.

• client (Optional[chromadb.Client]) –

• kwargs (Any) –

Returns

Chroma vectorstore.

Return type

Chroma

get(ids: Optional[OneOrMany[ID]] = None, where: Optional[Where] = None, limit: Optional[int] = None, offset: Optional[int] = None, where_document: Optional[WhereDocument] = None, include: Optional[List[str]] = None) → Dict[str, Any]

Gets the collection.

Parameters

• ids (Optional[OneOrMany[ID]]) – The ids of the embeddings to get. Optional.

• where (Optional[Where]) – A Where type dict used to filter results by. E.g. {“color” : “red”, “price”: 4.20}. Optional.

• limit (Optional[int]) – The number of documents to return. Optional.

• offset (Optional[int]) – The offset to start returning results from. Useful for paging results with limit. Optional.

• where_document (Optional[WhereDocument]) – A WhereDocument type dict used to filter by the documents. E.g. {$contains: “hello”}. Optional.

• include (Optional[List[str]]) – A list of what to include in the results. Can contain “embeddings”, “metadatas”, “documents”. Ids are always included. Defaults to [“metadatas”, “documents”]. Optional.

Return type

Dict[str, Any]

max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[Dict[str, str]] = None, where_document: Optional[Dict[str, str]] = None, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters

• query (str) – Text to look up documents similar to.

• k (int) – Number of Documents to return. Defaults to 4.

• fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.

• lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.

• filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.

• where_document (Optional[Dict[str, str]]) –

• kwargs (Any) –

Returns

List of Documents selected by maximal marginal relevance.

Return type

List[Document]

max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[Dict[str, str]] = None, where_document: Optional[Dict[str, str]] = None, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters

• embedding (List[float]) – Embedding to look up documents similar to.

• k (int) – Number of Documents to return. Defaults to 4.

• fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.

• lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.

• filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.

• where_document (Optional[Dict[str, str]]) –

• kwargs (Any) –

Returns

List of Documents selected by maximal marginal relevance.

Return type

List[Document]

persist() → None

Persist the collection.

This can be used to explicitly persist the data to disk. It will also be called automatically when the object is destroyed.

Return type

None

search(query: str, search_type: str, **kwargs: Any) → List[Document]

Return docs most similar to query using specified search type.

Parameters

• query (str) –

• search_type (str) –

• kwargs (Any) –

Return type

List[Document]

similarity_search(query: str, k: int = 4, filter: Optional[Dict[str, str]] = None, **kwargs: Any) → List[Document]

Run similarity search with Chroma.

Parameters

• query (str) – Query text to search for.

• k (int) – Number of results to return. Defaults to 4.

• filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.

• kwargs (Any) –

Returns

List of documents most similar to the query text.

Return type

List[Document]

similarity_search_by_vector(embedding: List[float], k: int = 4, filter: Optional[Dict[str, str]] = None, where_document: Optional[Dict[str, str]] = None, **kwargs: Any) → List[Document]

Return docs most similar to embedding vector. :param embedding: Embedding to look up documents similar to. :type embedding: List[float] :param k: Number of Documents to return. Defaults to 4. :type k: int :param filter: Filter by metadata. Defaults to None. :type filter: Optional[Dict[str, str]]

Returns

List of Documents most similar to the query vector.

Parameters

• embedding (List[float]) –

• k (int) –

• filter (Optional[Dict[str, str]]) –

• where_document (Optional[Dict[str, str]]) –

• kwargs (Any) –

Return type

List[Document]

similarity_search_by_vector_with_relevance_scores(embedding: List[float], k: int = 4, filter: Optional[Dict[str, str]] = None, where_document: Optional[Dict[str, str]] = None, **kwargs: Any) → List[Tuple[Document, float]]

Return docs most similar to embedding vector and similarity score.

Parameters

• embedding (List[float]) – Embedding to look up documents similar to.

• k (int) – Number of Documents to return. Defaults to 4.

• filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.

• where_document (Optional[Dict[str, str]]) –

• kwargs (Any) –

Returns

List of documents most similar to the query text and cosine distance in float for each. Lower score represents more similarity.

Return type

List[Tuple[Document, float]]

similarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → List[Tuple[Document, float]]

Return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

Parameters

• query (str) – input text

• k (int) – Number of Documents to return. Defaults to 4.

• **kwargs (Any) –

  kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

  filter the resulting set of retrieved docs

Returns

List of Tuples of (doc, similarity_score)

Return type

List[Tuple[Document, float]]

similarity_search_with_score(query: str, k: int = 4, filter: Optional[Dict[str, str]] = None, where_document: Optional[Dict[str, str]] = None, **kwargs: Any) → List[Tuple[Document, float]]

Run similarity search with Chroma with distance.

Parameters

• query (str) – Query text to search for.

• k (int) – Number of results to return. Defaults to 4.

• filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.

• where_document (Optional[Dict[str, str]]) –

• kwargs (Any) –

Returns

List of documents most similar to the query text and cosine distance in float for each. Lower score represents more similarity.

Return type

List[Tuple[Document, float]]

update_document(document_id: str, document: Document) → None

Update a document in the collection.

Parameters

• document_id (str) – ID of the document to update.

• document (Document) – Document to update.

Return type

None

update_documents(ids: List[str], documents: List[Document]) → None

Update a document in the collection.

Parameters

• ids (List[str]) – List of ids of the document to update.

• documents (List[Document]) – List of documents to update.

Return type

None

Examples using Chroma

• Chroma

• Combine agents and vector stores

• Confident

• Docugami

• Few-shot examples for chat models

• Improve document indexing with HyDE

• LOTR (Merger Retriever)

• Loading from LangChainHub

• Lost in the middle: The problem with long contexts

• Memory in the Multi-Input Chain

• MultiQueryRetriever

• MultiVector Retriever

• Ollama

• Parent Document Retriever

• Perform context-aware text splitting

• Psychic

• Question Answering

• RePhraseQueryRetriever

• Retrieve from vector stores directly

• Router

• SalesGPT - Your Context-Aware AI Sales Assistant With Knowledge Base

• Set env var OPENAI_API_KEY or load from a .env file

• Set env var OPENAI_API_KEY or load from a .env file:

• StarRocks

• Structure answers with OpenAI functions

• Use local LLMs

• Vectorstore

• WebResearchRetriever