docs: add page for Firestore Chat Message History integration (#15554)

- **Description:** Adds documentation for the
`FirestoreChatMessageHistory` integration and lists integration in
Google's documentation
  - **Issue:** NA
  - **Dependencies:** No

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
pull/16049/head
Averi Kitsch 9 months ago committed by GitHub
parent ddf4e7c633
commit ee378a0f40
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -0,0 +1,147 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "91c6a7ef",
"metadata": {},
"source": [
"# Google Cloud Firestore\n",
"\n",
"> [`Cloud Firestore`](https://cloud.google.com/firestore) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.\n",
"\n",
"This notebook goes over how to use Firestore to store chat message history."
]
},
{
"cell_type": "markdown",
"id": "2d6ed3c8-b70a-498c-bc9e-41b91797d3b7",
"metadata": {},
"source": [
"## Setting up"
]
},
{
"cell_type": "markdown",
"id": "b8eca282",
"metadata": {},
"source": [
"To run this notebook, you will need a Google Cloud Project, a Firestore database instance in Native Mode, and Google credentials, see [Firestore Quickstarts](https://cloud.google.com/firestore/docs/quickstarts)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5a7f3b3f-d9b8-4577-a7ef-bdd8ecaedb70",
"metadata": {},
"outputs": [],
"source": [
"!pip install firebase-admin"
]
},
{
"cell_type": "markdown",
"id": "a8e63850-3e14-46fe-a59e-be6d6bf8fe61",
"metadata": {},
"source": [
"## Basic Usage"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "d15e3302",
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.chat_message_histories.firestore import (\n",
" FirestoreChatMessageHistory,\n",
")\n",
"\n",
"message_history = FirestoreChatMessageHistory(\n",
" collection_name=\"langchain-chat-history\",\n",
" session_id=\"user-session-id\",\n",
" user_id=\"user-id\",\n",
")\n",
"\n",
"message_history.add_user_message(\"hi!\")\n",
"message_history.add_ai_message(\"whats up?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "64fc465e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[HumanMessage(content='hi!'),\n",
" HumanMessage(content='hi!'),\n",
" AIMessage(content='whats up?')]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"message_history.messages"
]
},
{
"cell_type": "markdown",
"id": "4be8576e",
"metadata": {},
"source": [
"## Custom Firestore Client"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "12999273",
"metadata": {},
"outputs": [],
"source": [
"import firebase_admin\n",
"from firebase_admin import credentials, firestore\n",
"\n",
"# Use a service account.\n",
"cred = credentials.Certificate(\"path/to/serviceAccount.json\")\n",
"\n",
"app = firebase_admin.initialize_app(cred)\n",
"client = firestore.client(app=app)\n",
"\n",
"message_history = FirestoreChatMessageHistory(\n",
" collection_name=\"langchain-chat-history\",\n",
" session_id=\"user-session-id\",\n",
" user_id=\"user-id\",\n",
" firestore_client=client,\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

@ -186,7 +186,7 @@ from langchain_community.document_loaders import GoogleSpeechToTextLoader
### Google Vertex AI Vector Search
> [Google Vertex AI Vector Search](https://cloud.google.com/vertex-ai/docs/matching-engine/overview),
> formerly known as `Vertex AI Matching Engine`, provides the industry's leading high-scale
> formerly known as `Vertex AI Matching Engine`, provides the industry's leading high-scale
> low latency vector database. These vector databases are commonly
> referred to as vector similarity-matching or an approximate nearest neighbor (ANN) service.
@ -207,7 +207,7 @@ from langchain_community.vectorstores import MatchingEngine
> [Google BigQuery](https://cloud.google.com/bigquery),
> BigQuery is a serverless and cost-effective enterprise data warehouse in Google Cloud.
>
> Google BigQuery Vector Search
> Google BigQuery Vector Search
> BigQuery vector search lets you use GoogleSQL to do semantic search, using vector indexes for fast but approximate results, or using brute force for exact results.
> It can calculate Euclidean or Cosine distance. With LangChain, we default to use Euclidean distance.
@ -228,7 +228,7 @@ from langchain.vectorstores import BigQueryVectorSearch
>[Google ScaNN](https://github.com/google-research/google-research/tree/master/scann)
> (Scalable Nearest Neighbors) is a python package.
>
>
>`ScaNN` is a method for efficient vector similarity search at scale.
>`ScaNN` includes search space pruning and quantization for Maximum Inner
@ -285,9 +285,9 @@ from langchain.retrievers import GoogleVertexAISearchRetriever
### Document AI Warehouse
> [Google Cloud Document AI Warehouse](https://cloud.google.com/document-ai-warehouse)
> allows enterprises to search, store, govern, and manage documents and their AI-extracted
> allows enterprises to search, store, govern, and manage documents and their AI-extracted
> data and metadata in a single platform.
>
>
```python
from langchain.retrievers import GoogleDocumentAIWarehouseRetriever
@ -304,9 +304,9 @@ documents = docai_wh_retriever.get_relevant_documents(
### Google Cloud Text-to-Speech
>[Google Cloud Text-to-Speech](https://cloud.google.com/text-to-speech) enables developers to
> synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants.
> It applies DeepMinds groundbreaking research in WaveNet and Googles powerful neural networks
>[Google Cloud Text-to-Speech](https://cloud.google.com/text-to-speech) enables developers to
> synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants.
> It applies DeepMinds groundbreaking research in WaveNet and Googles powerful neural networks
> to deliver the highest fidelity possible.
We need to install a python package.
@ -354,7 +354,7 @@ from langchain.tools import GooglePlacesTool
### Google Search
- Set up a Custom Search Engine, following [these instructions](https://stackoverflow.com/questions/37083058/programmatically-searching-google-in-python-using-custom-search)
- Get an API Key and Custom Search Engine ID from the previous step, and set them as environment variables
- Get an API Key and Custom Search Engine ID from the previous step, and set them as environment variables
`GOOGLE_API_KEY` and `GOOGLE_CSE_ID` respectively.
```python
@ -444,12 +444,12 @@ from langchain_community.utilities.google_trends import GoogleTrendsAPIWrapper
### Google Document AI
>[Document AI](https://cloud.google.com/document-ai/docs/overview) is a `Google Cloud Platform`
> service that transforms unstructured data from documents into structured data, making it easier
>[Document AI](https://cloud.google.com/document-ai/docs/overview) is a `Google Cloud Platform`
> service that transforms unstructured data from documents into structured data, making it easier
> to understand, analyze, and consume.
We need to set up a [`GCS` bucket and create your own OCR processor](https://cloud.google.com/document-ai/docs/create-processor)
The `GCS_OUTPUT_PATH` should be a path to a folder on GCS (starting with `gs://`)
We need to set up a [`GCS` bucket and create your own OCR processor](https://cloud.google.com/document-ai/docs/create-processor)
The `GCS_OUTPUT_PATH` should be a path to a folder on GCS (starting with `gs://`)
and a processor name should look like `projects/PROJECT_NUMBER/locations/LOCATION/processors/PROCESSOR_ID`.
We can get it either programmatically or copy from the `Prediction endpoint` section of the `Processor details`
tab in the Google Cloud Console.
@ -507,6 +507,23 @@ See a [usage example and authorization instructions](/docs/integrations/toolkits
from langchain_community.agent_toolkits import GmailToolkit
```
## Memory
### Cloud Firestore
> [`Cloud Firestore`](https://cloud.google.com/firestore) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.
First, we need to install the python package.
```bash
pip install firebase-admin
```
See a [usage example and authorization instructions](/docs/integrations/memory/firestore_chat_message_history).
```python
from langchain_community.chat_message_histories.firestore import FirestoreChatMessageHistory
```
## Chat Loaders
@ -560,7 +577,7 @@ from langchain_community.utilities import GoogleSerperAPIWrapper
### YouTube
>[YouTube Search](https://github.com/joetats/youtube_search) package searches `YouTube` videos avoiding using their heavily rate-limited API.
>
>
>It uses the form on the YouTube homepage and scrapes the resulting page.
We need to install a python package.

Loading…
Cancel
Save