Fix update_document function, add test and documentation. (#5359)

# Fix for `update_document` Function in Chroma

## Summary
This pull request addresses an issue with the `update_document` function
in the Chroma class, as described in
[#5031](https://github.com/hwchase17/langchain/issues/5031#issuecomment-1562577947).
The issue was identified as an `AttributeError` raised when calling
`update_document` due to a missing corresponding method in the
`Collection` object. This fix refactors the `update_document` method in
`Chroma` to correctly interact with the `Collection` object.

## Changes
1. Fixed the `update_document` method in the `Chroma` class to correctly
call methods on the `Collection` object.
2. Added the corresponding test `test_chroma_update_document` in
`tests/integration_tests/vectorstores/test_chroma.py` to reflect the
updated method call.
3. Added an example and explanation of how to use the `update_document`
function in the Jupyter notebook tutorial for Chroma.

## Test Plan
All existing tests pass after this change. In addition, the
`test_chroma_update_document` test case now correctly checks the
functionality of `update_document`, ensuring that the function works as
expected and updates the content of documents correctly.

## Reviewers
@dev2049

This fix will ensure that users are able to use the `update_document`
function as expected, without encountering the previous
`AttributeError`. This will enhance the usability and reliability of the
Chroma class for all users.

Thank you for considering this pull request. I look forward to your
feedback and suggestions.

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

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
@@ -33,7 +34,7 @@
    },
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       " ········\n"
@@ -86,7 +87,6 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.document_loaders import TextLoader\n",
     "loader = TextLoader('../../../state_of_the_union.txt')\n",
     "documents = loader.load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
@@ -143,6 +143,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "18152965",
    "metadata": {},
@@ -187,6 +188,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "8061454b",
    "metadata": {},
@@ -197,6 +199,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "2b76db26",
    "metadata": {},
@@ -232,6 +235,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "f568a322",
    "metadata": {},
@@ -262,6 +266,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "cc9ed900",
    "metadata": {},
@@ -292,6 +297,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "794a7552",
    "metadata": {},
@@ -336,13 +342,81 @@
     "retriever.get_relevant_documents(query)[0]"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "2a877f08",
+   "metadata": {},
+   "source": [
+    "## Updating a Document\n",
+    "The `update_document` function allows you to modify the content of a document in the Chroma instance after it has been added. Let's see an example of how to use this function."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
    "id": "a559c3f1",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "# Import Document class\n",
+    "from langchain.docstore.document import Document\n",
+    "\n",
+    "# Initial document content and id\n",
+    "initial_content = \"This is an initial document content\"\n",
+    "document_id = \"doc1\"\n",
+    "\n",
+    "# Create an instance of Document with initial content and metadata\n",
+    "original_doc = Document(page_content=initial_content, metadata={\"page\": \"0\"})\n",
+    "\n",
+    "# Initialize a Chroma instance with the original document\n",
+    "new_db = Chroma.from_documents(\n",
+    "    collection_name=\"test_collection\",\n",
+    "    documents=[original_doc],\n",
+    "    embedding=OpenAIEmbeddings(),  # using the same embeddings as before\n",
+    "    ids=[document_id],\n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "60a7c273",
+   "metadata": {},
+   "source": [
+    "At this point, we have a new Chroma instance with a single document \"This is an initial document content\" with id \"doc1\". Now, let's update the content of the document."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "55e48056",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This is the updated document content {'page': '1'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Updated document content\n",
+    "updated_content = \"This is the updated document content\"\n",
+    "\n",
+    "# Create a new Document instance with the updated content\n",
+    "updated_doc = Document(page_content=updated_content, metadata={\"page\": \"1\"})\n",
+    "\n",
+    "# Update the document in the Chroma instance by passing the document id and the updated document\n",
+    "new_db.update_document(document_id=document_id, document=updated_doc)\n",
+    "\n",
+    "# Now, let's retrieve the updated document using similarity search\n",
+    "output = new_db.similarity_search(updated_content, k=1)\n",
+    "\n",
+    "# Print the content of the retrieved document\n",
+    "print(output[0].page_content, output[0].metadata)"
+   ]
   }
  ],
  "metadata": {

langchain/vectorstores/chroma.py

@@ -348,7 +348,18 @@ class Chroma(VectorStore):
         """
         text = document.page_content
         metadata = document.metadata
-        self._collection.update_document(document_id, text, metadata)
+        if self._embedding_function is None:
+            raise ValueError(
+                "For update, you must specify an embedding function on creation."
+            )
+        embeddings = self._embedding_function.embed_documents(list(text))
+
+        self._collection.update(
+            ids=[document_id],
+            embeddings=[embeddings[0]],
+            documents=[text],
+            metadatas=[metadata],
+        )
 
     @classmethod
     def from_texts(

tests/integration_tests/vectorstores/test_chroma.py

@@ -160,3 +160,37 @@ def test_chroma_with_include_parameter() -> None:
     assert output["embeddings"] is not None
     output = docsearch.get()
     assert output["embeddings"] is None
+
+
+def test_chroma_update_document() -> None:
+    """Test the update_document function in the Chroma class."""
+
+    # Initial document content and id
+    initial_content = "foo"
+    document_id = "doc1"
+
+    # Create an instance of Document with initial content and metadata
+    original_doc = Document(page_content=initial_content, metadata={"page": "0"})
+
+    # Initialize a Chroma instance with the original document
+    docsearch = Chroma.from_documents(
+        collection_name="test_collection",
+        documents=[original_doc],
+        embedding=FakeEmbeddings(),
+        ids=[document_id],
+    )
+
+    # Define updated content for the document
+    updated_content = "updated foo"
+
+    # Create a new Document instance with the updated content and the same id
+    updated_doc = Document(page_content=updated_content, metadata={"page": "0"})
+
+    # Update the document in the Chroma instance
+    docsearch.update_document(document_id=document_id, document=updated_doc)
+
+    # Perform a similarity search with the updated content
+    output = docsearch.similarity_search(updated_content, k=1)
+
+    # Assert that the updated document is returned by the search
+    assert output == [Document(page_content=updated_content, metadata={"page": "0"})]