mirror of https://github.com/hwchase17/langchain
Community: Updating Azure Retriever and Docs to be Azure AI Search instead of Azure Cognitive Search (#19925)
Last year Microsoft [changed the name](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) of Azure Cognitive Search to Azure AI Search. This PR updates the Langchain Azure Retriever API and it's associated docs to reflect this change. It may be confusing for users to see the name Cognitive here and AI in the Microsoft documentation which is why this is needed. I've also added a more detailed example to the Azure retriever doc page. There are more places that need a similar update but I'm breaking it up so the PRs are not too big 😄 Fixing my errors from the previous PR. Twitter: @marlene_zw Two new tests added to test backward compatibility in `libs/community/tests/integration_tests/retrievers/test_azure_cognitive_search.py` --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>pull/9293/merge
parent
820b713086
commit
2f03bc397e
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@ -1,147 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1edb9e6b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Azure Cognitive Search\n",
|
||||
"\n",
|
||||
">[Azure Cognitive Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search`) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.\n",
|
||||
"\n",
|
||||
">Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you'll work with the following capabilities:\n",
|
||||
">- A search engine for full text search over a search index containing user-owned content\n",
|
||||
">- Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation\n",
|
||||
">- Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more\n",
|
||||
">- Programmability through REST APIs and client libraries in Azure SDKs\n",
|
||||
">- Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)\n",
|
||||
"\n",
|
||||
"This notebook shows how to use Azure Cognitive Search (ACS) within LangChain."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "074b0004",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Set up Azure Cognitive Search\n",
|
||||
"\n",
|
||||
"To set up ACS, please follow the instructions [here](https://learn.microsoft.com/en-us/azure/search/search-create-service-portal).\n",
|
||||
"\n",
|
||||
"Please note\n",
|
||||
"1. the name of your ACS service, \n",
|
||||
"2. the name of your ACS index,\n",
|
||||
"3. your API key.\n",
|
||||
"\n",
|
||||
"Your API key can be either Admin or Query key, but as we only read data it is recommended to use a Query key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0474661d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using the Azure Cognitive Search Retriever"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "39d6074e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"from langchain_community.retrievers import (\n",
|
||||
" AzureCognitiveSearchRetriever,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b7243e6d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Set Service Name, Index Name and API key as environment variables (alternatively, you can pass them as arguments to `AzureCognitiveSearchRetriever`)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "33fd23d1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"AZURE_COGNITIVE_SEARCH_SERVICE_NAME\"] = \"<YOUR_ACS_SERVICE_NAME>\"\n",
|
||||
"os.environ[\"AZURE_COGNITIVE_SEARCH_INDEX_NAME\"] = \"<YOUR_ACS_INDEX_NAME>\"\n",
|
||||
"os.environ[\"AZURE_COGNITIVE_SEARCH_API_KEY\"] = \"<YOUR_API_KEY>\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "057deaad",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Create the Retriever"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c18d0c4c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"retriever = AzureCognitiveSearchRetriever(content_key=\"content\", top_k=10)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e94ea104",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now you can use retrieve documents from Azure Cognitive Search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c8b5794b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"retriever.get_relevant_documents(\"what is langchain\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "72eca08e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can change the number of results returned with the `top_k` parameter. The default value is `None`, which returns all results. "
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.10.12"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -0,0 +1,70 @@
|
||||
"""Test Azure AI Search wrapper."""
|
||||
from langchain_core.documents import Document
|
||||
|
||||
from langchain_community.retrievers.azure_ai_search import (
|
||||
AzureAISearchRetriever,
|
||||
AzureCognitiveSearchRetriever,
|
||||
)
|
||||
|
||||
|
||||
def test_azure_ai_search_get_relevant_documents() -> None:
|
||||
"""Test valid call to Azure AI Search.
|
||||
|
||||
In order to run this test, you should provide
|
||||
a `service_name`, azure search `api_key` and an `index_name`
|
||||
as arguments for the AzureAISearchRetriever in both tests.
|
||||
api_version, aiosession and topk_k are optional parameters.
|
||||
"""
|
||||
retriever = AzureAISearchRetriever()
|
||||
|
||||
documents = retriever.get_relevant_documents("what is langchain?")
|
||||
for doc in documents:
|
||||
assert isinstance(doc, Document)
|
||||
assert doc.page_content
|
||||
|
||||
retriever = AzureAISearchRetriever(top_k=1)
|
||||
documents = retriever.get_relevant_documents("what is langchain?")
|
||||
assert len(documents) <= 1
|
||||
|
||||
|
||||
async def test_azure_ai_search_aget_relevant_documents() -> None:
|
||||
"""Test valid async call to Azure AI Search.
|
||||
|
||||
In order to run this test, you should provide
|
||||
a `service_name`, azure search `api_key` and an `index_name`
|
||||
as arguments for the AzureAISearchRetriever.
|
||||
"""
|
||||
retriever = AzureAISearchRetriever()
|
||||
documents = await retriever.aget_relevant_documents("what is langchain?")
|
||||
for doc in documents:
|
||||
assert isinstance(doc, Document)
|
||||
assert doc.page_content
|
||||
|
||||
|
||||
def test_azure_cognitive_search_get_relevant_documents() -> None:
|
||||
"""Test valid call to Azure Cognitive Search.
|
||||
|
||||
This is to test backwards compatibility of the retriever
|
||||
"""
|
||||
retriever = AzureCognitiveSearchRetriever()
|
||||
|
||||
documents = retriever.get_relevant_documents("what is langchain?")
|
||||
for doc in documents:
|
||||
assert isinstance(doc, Document)
|
||||
assert doc.page_content
|
||||
|
||||
retriever = AzureCognitiveSearchRetriever(top_k=1)
|
||||
documents = retriever.get_relevant_documents("what is langchain?")
|
||||
assert len(documents) <= 1
|
||||
|
||||
|
||||
async def test_azure_cognitive_search_aget_relevant_documents() -> None:
|
||||
"""Test valid async call to Azure Cognitive Search.
|
||||
|
||||
This is to test backwards compatibility of the retriever
|
||||
"""
|
||||
retriever = AzureCognitiveSearchRetriever()
|
||||
documents = await retriever.aget_relevant_documents("what is langchain?")
|
||||
for doc in documents:
|
||||
assert isinstance(doc, Document)
|
||||
assert doc.page_content
|
@ -1,37 +0,0 @@
|
||||
"""Test Azure Cognitive Search wrapper."""
|
||||
from langchain_core.documents import Document
|
||||
|
||||
from langchain_community.retrievers.azure_cognitive_search import (
|
||||
AzureCognitiveSearchRetriever,
|
||||
)
|
||||
|
||||
|
||||
def test_azure_cognitive_search_get_relevant_documents() -> None:
|
||||
"""Test valid call to Azure Cognitive Search.
|
||||
|
||||
In order to run this test, you should provide a service name, azure search api key
|
||||
and an index_name as arguments for the AzureCognitiveSearchRetriever in both tests.
|
||||
"""
|
||||
retriever = AzureCognitiveSearchRetriever()
|
||||
|
||||
documents = retriever.get_relevant_documents("what is langchain?")
|
||||
for doc in documents:
|
||||
assert isinstance(doc, Document)
|
||||
assert doc.page_content
|
||||
|
||||
retriever = AzureCognitiveSearchRetriever()
|
||||
documents = retriever.get_relevant_documents("what is langchain?")
|
||||
assert len(documents) <= 1
|
||||
|
||||
|
||||
async def test_azure_cognitive_search_aget_relevant_documents() -> None:
|
||||
"""Test valid async call to Azure Cognitive Search.
|
||||
|
||||
In order to run this test, you should provide a service name, azure search api key
|
||||
and an index_name as arguments for the AzureCognitiveSearchRetriever.
|
||||
"""
|
||||
retriever = AzureCognitiveSearchRetriever()
|
||||
documents = await retriever.aget_relevant_documents("what is langchain?")
|
||||
for doc in documents:
|
||||
assert isinstance(doc, Document)
|
||||
assert doc.page_content
|
@ -0,0 +1,6 @@
|
||||
from langchain_community.retrievers.azure_ai_search import (
|
||||
AzureAISearchRetriever,
|
||||
AzureCognitiveSearchRetriever,
|
||||
)
|
||||
|
||||
__all__ = ["AzureAISearchRetriever", "AzureCognitiveSearchRetriever"]
|
@ -1,5 +0,0 @@
|
||||
from langchain_community.retrievers.azure_cognitive_search import (
|
||||
AzureCognitiveSearchRetriever,
|
||||
)
|
||||
|
||||
__all__ = ["AzureCognitiveSearchRetriever"]
|
Loading…
Reference in New Issue