github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-25 16:13:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/kwargs loaders (#1588)

Browse Source 
Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>
This commit is contained in:
Harrison Chase 2023-03-10 15:05:06 -08:00 committed by GitHub
parent 9f78717b3c
commit 8dba30f31e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
langchain/indexes/vectorstore.py
View File

@ -50,8 +50,9 @@ class VectorstoreIndexCreator(BaseModel):
"""Logic for creating indexes.""" """Logic for creating indexes."""
vectorstore_cls: Type[VectorStore] = Chroma vectorstore_cls: Type[VectorStore] = Chroma
embedding: Embeddings = Field(default_factory=OpenAIEmbeddings)
text_splitter: TextSplitter = Field(default_factory=_get_default_text_splitter) text_splitter: TextSplitter = Field(default_factory=_get_default_text_splitter)
embedding: Embeddings = Field(default_factory=OpenAIEmbeddings)
vectorstore_kwargs: dict = Field(default_factory=dict)
class Config: class Config:
"""Configuration for this pydantic object.""" """Configuration for this pydantic object."""
@ -65,5 +66,7 @@ class VectorstoreIndexCreator(BaseModel):
for loader in loaders: for loader in loaders:
docs.extend(loader.load()) docs.extend(loader.load())
sub_docs = self.text_splitter.split_documents(docs) sub_docs = self.text_splitter.split_documents(docs)
vectorstore = self.vectorstore_cls.from_documents(sub_docs, self.embedding) vectorstore = self.vectorstore_cls.from_documents(
sub_docs, self.embedding, **self.vectorstore_kwargs
)
return VectorStoreIndexWrapper(vectorstore=vectorstore) return VectorStoreIndexWrapper(vectorstore=vectorstore)

3
langchain/vectorstores/chroma.py
View File

@ -230,6 +230,7 @@ class Chroma(VectorStore):
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.
client_settings (Optional[chromadb.config.Settings]): Chroma client settings
Returns: Returns:
Chroma: Chroma vectorstore. Chroma: Chroma vectorstore.
@ -264,7 +265,7 @@ class Chroma(VectorStore):
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 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
Returns: Returns:
Chroma: Chroma vectorstore. Chroma: Chroma vectorstore.
""" """