blob42/langchain
1
0
Fork 0
forked from Archives/langchain
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[bugfix] Fix persisted chromadb vectorstore (#1444)

Browse Source 
If a `persist_directory` param was set, chromadb would throw a warning
that ""No embedding_function provided, using default embedding function:
SentenceTransformerEmbeddingFunction". and would error with a `Illegal
instruction: 4` error.

This is on a MBP M1 13.2.1, python 3.9.

I'm not entirely sure why that error happened, but when using
`get_or_create_collection` instead of `list_collection` on our end, the
error and warning goes away and chroma works as expected.

Added bonus this is cleaner and likely more efficient.
`list_collections` builds a new `Collection` instance for each collect,
then `Chroma` would just use the `name` field to tell if the collection
existed.
This commit is contained in:
Tim Asp 2023-03-10 15:14:35 -08:00 committed by GitHub
parent 8dba30f31e
commit 01a57198b8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
langchain/vectorstores/chroma.py
View File

@ -78,17 +78,7 @@ class Chroma(VectorStore):
self._client = chromadb.Client(self._client_settings) self._client = chromadb.Client(self._client_settings)
self._embedding_function = embedding_function self._embedding_function = embedding_function
self._persist_directory = persist_directory self._persist_directory = persist_directory
self._collection = self._client.get_or_create_collection(
# Check if the collection exists, create it if not
if collection_name in [col.name for col in self._client.list_collections()]:
self._collection = self._client.get_collection(name=collection_name)
# TODO: Persist the user's embedding function
logger.warning(
f"Collection {collection_name} already exists,"
" Do you have the right embedding function?"
)
else:
self._collection = self._client.create_collection(
name=collection_name, name=collection_name,
embedding_function=self._embedding_function.embed_documents embedding_function=self._embedding_function.embed_documents
if self._embedding_function is not None if self._embedding_function is not None
@ -224,9 +214,9 @@ class Chroma(VectorStore):
Otherwise, the data will be ephemeral in-memory. Otherwise, the data will be ephemeral in-memory.
Args: Args:
texts (List[str]): List of texts to add to the collection.
collection_name (str): Name of the collection to create. collection_name (str): Name of the collection to create.
persist_directory (Optional[str]): Directory to persist the collection. persist_directory (Optional[str]): Directory to persist the collection.
documents (List[Document]): List of documents to add.
embedding (Optional[Embeddings]): Embedding function. Defaults to None. embedding (Optional[Embeddings]): Embedding function. Defaults to None.
metadatas (Optional[List[dict]]): List of metadatas. Defaults to None. metadatas (Optional[List[dict]]): List of metadatas. Defaults to None.
ids (Optional[List[str]]): List of document IDs. Defaults to None. ids (Optional[List[str]]): List of document IDs. Defaults to None.
@ -263,6 +253,7 @@ class Chroma(VectorStore):
Args: Args:
collection_name (str): Name of the collection to create. collection_name (str): Name of the collection to create.
persist_directory (Optional[str]): Directory to persist the collection. 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. documents (List[Document]): List of documents to add to the vectorstore.
embedding (Optional[Embeddings]): Embedding function. Defaults to None. embedding (Optional[Embeddings]): Embedding function. Defaults to None.
client_settings (Optional[chromadb.config.Settings]): Chroma client settings client_settings (Optional[chromadb.config.Settings]): Chroma client settings