clean

docs/modules/indexes/document_loaders/examples/docugami.ipynb

@@ -156,7 +156,7 @@
    ],
    "source": [
     "embedding = OpenAIEmbeddings()\n",
-    "vectordb = Chroma.from_documents(documents=documents, embedding=embedding)\n",
+    "vectordb = Chroma.from_documents(documents, embedding)\n",
     "retriever = vectordb.as_retriever()\n",
     "qa_chain = RetrievalQA.from_chain_type(\n",
     "    llm=OpenAI(), chain_type=\"stuff\", retriever=retriever, return_source_documents=True\n",
@@ -326,7 +326,7 @@
     "\n",
     "document_content_description = \"Contents of this chunk\"\n",
     "llm = OpenAI(temperature=0)\n",
-    "vectordb = Chroma.from_documents(documents=documents, embedding=embedding)\n",
+    "vectordb = Chroma.from_documents(documents, embedding)\n",
     "retriever = SelfQueryRetriever.from_llm(\n",
     "    llm, vectordb, document_content_description, metadata_field_info, verbose=True\n",
     ")\n",
@@ -398,7 +398,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.10"
+   "version": "3.11.3"
   }
  },
  "nbformat": 4,

docs/modules/indexes/vectorstores/examples/chroma.ipynb

@@ -228,7 +228,7 @@
     "persist_directory = 'db'\n",
     "\n",
     "embedding = OpenAIEmbeddings()\n",
-    "vectordb = Chroma.from_documents(documents=docs, embedding=embedding, persist_directory=persist_directory)"
+    "vectordb = Chroma.from_documents(docs, embedding, persist_directory=persist_directory)"
    ]
   },
   {
@@ -361,7 +361,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.3"
   }
  },
  "nbformat": 4,

langchain/vectorstores/chroma.py

@@ -90,6 +90,7 @@ class Chroma(VectorStore):
 
         self._embedding_function = embedding_function
         self._persist_directory = persist_directory
+
         self._collection = self._client.get_or_create_collection(
             name=collection_name,
             embedding_function=self._embedding_function.embed_documents
@@ -354,7 +355,7 @@ class Chroma(VectorStore):
     def from_texts(
         cls: Type[Chroma],
         texts: List[str],
-        embedding: Optional[Embeddings] = None,
+        embedding: Embeddings,
         metadatas: Optional[List[dict]] = None,
         ids: Optional[List[str]] = None,
         collection_name: str = _LANGCHAIN_DEFAULT_COLLECTION_NAME,
@@ -389,43 +390,3 @@ class Chroma(VectorStore):
         )
         chroma_collection.add_texts(texts=texts, metadatas=metadatas, ids=ids)
         return chroma_collection
-
-    @classmethod
-    def from_documents(
-        cls: Type[Chroma],
-        documents: List[Document],
-        embedding: Optional[Embeddings] = None,
-        ids: Optional[List[str]] = None,
-        collection_name: str = _LANGCHAIN_DEFAULT_COLLECTION_NAME,
-        persist_directory: Optional[str] = None,
-        client_settings: Optional[chromadb.config.Settings] = None,
-        client: Optional[chromadb.Client] = None,  # Add this line
-        **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.
-
-        Args:
-            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
-        Returns:
-            Chroma: Chroma vectorstore.
-        """
-        texts = [doc.page_content for doc in documents]
-        metadatas = [doc.metadata for doc in documents]
-        return cls.from_texts(
-            texts=texts,
-            embedding=embedding,
-            metadatas=metadatas,
-            ids=ids,
-            collection_name=collection_name,
-            persist_directory=persist_directory,
-            client_settings=client_settings,
-            client=client,
-        )

tests/integration_tests/vectorstores/test_chroma.py

@@ -10,7 +10,9 @@ def test_chroma() -> None:
     """Test end to end construction and search."""
     texts = ["foo", "bar", "baz"]
     docsearch = Chroma.from_texts(
-        collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
+        texts,
+        FakeEmbeddings(),
+        collection_name="test_collection",
     )
     output = docsearch.similarity_search("foo", k=1)
     assert output == [Document(page_content="foo")]
@@ -21,7 +23,9 @@ async def test_chroma_async() -> None:
     """Test end to end construction and search."""
     texts = ["foo", "bar", "baz"]
     docsearch = Chroma.from_texts(
-        collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
+        texts,
+        FakeEmbeddings(),
+        collection_name="test_collection",
     )
     output = await docsearch.asimilarity_search("foo", k=1)
     assert output == [Document(page_content="foo")]
@@ -32,9 +36,9 @@ def test_chroma_with_metadatas() -> None:
     texts = ["foo", "bar", "baz"]
     metadatas = [{"page": str(i)} for i in range(len(texts))]
     docsearch = Chroma.from_texts(
+        texts,
+        FakeEmbeddings(),
         collection_name="test_collection",
-        texts=texts,
-        embedding=FakeEmbeddings(),
         metadatas=metadatas,
     )
     output = docsearch.similarity_search("foo", k=1)
@@ -46,9 +50,9 @@ def test_chroma_with_metadatas_with_scores() -> None:
     texts = ["foo", "bar", "baz"]
     metadatas = [{"page": str(i)} for i in range(len(texts))]
     docsearch = Chroma.from_texts(
+        texts,
+        FakeEmbeddings(),
         collection_name="test_collection",
-        texts=texts,
-        embedding=FakeEmbeddings(),
         metadatas=metadatas,
     )
     output = docsearch.similarity_search_with_score("foo", k=1)
@@ -60,9 +64,9 @@ def test_chroma_search_filter() -> None:
     texts = ["far", "bar", "baz"]
     metadatas = [{"first_letter": "{}".format(text[0])} for text in texts]
     docsearch = Chroma.from_texts(
+        texts,
+        FakeEmbeddings(),
         collection_name="test_collection",
-        texts=texts,
-        embedding=FakeEmbeddings(),
         metadatas=metadatas,
     )
     output = docsearch.similarity_search("far", k=1, filter={"first_letter": "f"})
@@ -76,9 +80,9 @@ def test_chroma_search_filter_with_scores() -> None:
     texts = ["far", "bar", "baz"]
     metadatas = [{"first_letter": "{}".format(text[0])} for text in texts]
     docsearch = Chroma.from_texts(
+        texts,
+        FakeEmbeddings(),
         collection_name="test_collection",
-        texts=texts,
-        embedding=FakeEmbeddings(),
         metadatas=metadatas,
     )
     output = docsearch.similarity_search_with_score(
@@ -101,9 +105,9 @@ def test_chroma_with_persistence() -> None:
     collection_name = "test_collection"
     texts = ["foo", "bar", "baz"]
     docsearch = Chroma.from_texts(
+        texts,
+        FakeEmbeddings(),
         collection_name=collection_name,
-        texts=texts,
-        embedding=FakeEmbeddings(),
         persist_directory=chroma_persist_dir,
     )
 
@@ -132,7 +136,9 @@ def test_chroma_mmr() -> None:
     """Test end to end construction and search."""
     texts = ["foo", "bar", "baz"]
     docsearch = Chroma.from_texts(
-        collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
+        texts,
+        FakeEmbeddings(),
+        collection_name="test_collection",
     )
     output = docsearch.max_marginal_relevance_search("foo", k=1)
     assert output == [Document(page_content="foo")]
@@ -143,7 +149,9 @@ def test_chroma_mmr_by_vector() -> None:
     texts = ["foo", "bar", "baz"]
     embeddings = FakeEmbeddings()
     docsearch = Chroma.from_texts(
-        collection_name="test_collection", texts=texts, embedding=embeddings
+        texts,
+        embeddings,
+        collection_name="test_collection",
     )
     embedded_query = embeddings.embed_query("foo")
     output = docsearch.max_marginal_relevance_search_by_vector(embedded_query, k=1)
@@ -154,7 +162,9 @@ def test_chroma_with_include_parameter() -> None:
     """Test end to end construction and include parameter."""
     texts = ["foo", "bar", "baz"]
     docsearch = Chroma.from_texts(
-        collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
+        texts,
+        FakeEmbeddings(),
+        collection_name="test_collection",
     )
     output = docsearch.get(include=["embeddings"])
     assert output["embeddings"] is not None