docs: Update Azure Search vector store notebook (#17901)

- **Description:** Update the Azure Search vector store notebook for the
latest version of the SDK

---------

Co-authored-by: Matt Gotteiner <[email protected]>
pull/16856/head
Matt 7 months ago committed by GitHub
parent c05cbf0533
commit 6ef12fdfd2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

@ -25,7 +25,7 @@
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet azure-search-documents\n",
"%pip install --upgrade --quiet azure-search-documents==11.4.0\n",
"%pip install --upgrade --quiet azure-identity"
]
},
@ -39,14 +39,14 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"from langchain_community.vectorstores.azuresearch import AzureSearch\n",
"from langchain_openai import OpenAIEmbeddings"
"from langchain_openai import AzureOpenAIEmbeddings"
]
},
{
@ -60,15 +60,16 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"os.environ[\"OPENAI_API_TYPE\"] = \"azure\"\n",
"os.environ[\"OPENAI_API_BASE\"] = \"YOUR_OPENAI_ENDPOINT\"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"YOUR_OPENAI_API_KEY\"\n",
"os.environ[\"OPENAI_API_VERSION\"] = \"2023-05-15\"\n",
"model: str = \"text-embedding-ada-002\""
"embeddings: AzureOpenAIEmbeddings = AzureOpenAIEmbeddings(\n",
" azure_deployment=\"text-embedding-ada-002\",\n",
" openai_api_version=\"2023-05-15\",\n",
" azure_endpoint=\"YOUR_AZURE_OPENAI_ENDPOINT\",\n",
" api_key=\"YOUR_AZURE_OPENAI_KEY\",\n",
")"
]
},
{
@ -82,7 +83,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -101,11 +102,10 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"embeddings: OpenAIEmbeddings = OpenAIEmbeddings(deployment=model, chunk_size=1)\n",
"index_name: str = \"langchain-vector-demo\"\n",
"vector_store: AzureSearch = AzureSearch(\n",
" azure_search_endpoint=vector_store_address,\n",
@ -154,23 +154,9 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while youre at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, Id like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nations top legal minds, who will continue Justice Breyers legacy of excellence.\n"
]
}
],
"outputs": [],
"source": [
"# Perform a similarity search\n",
"docs = vector_store.similarity_search(\n",
@ -192,24 +178,9 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[(Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while youre at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, Id like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nations top legal minds, who will continue Justice Breyers legacy of excellence.', metadata={'source': 'C:\\\\repos\\\\langchain-fruocco-acs\\\\langchain\\\\docs\\\\extras\\\\modules\\\\state_of_the_union.txt'}),\n",
" 0.8441472),\n",
" (Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while youre at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, Id like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nations top legal minds, who will continue Justice Breyers legacy of excellence.', metadata={'source': 'C:\\\\repos\\\\langchain-fruocco-acs\\\\langchain\\\\docs\\\\extras\\\\modules\\\\state_of_the_union.txt'}),\n",
" 0.8441472),\n",
" (Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since shes been nominated, shes received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, weve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWeve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWere putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWere securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': 'C:\\\\repos\\\\langchain-fruocco-acs\\\\langchain\\\\docs\\\\extras\\\\modules\\\\state_of_the_union.txt'}),\n",
" 0.82153815),\n",
" (Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since shes been nominated, shes received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, weve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWeve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWere putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWere securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': 'C:\\\\repos\\\\langchain-fruocco-acs\\\\langchain\\\\docs\\\\extras\\\\modules\\\\state_of_the_union.txt'}),\n",
" 0.82153815)]\n"
]
}
],
"outputs": [],
"source": [
"docs_and_scores = vector_store.similarity_search_with_relevance_scores(\n",
" query=\"What did the president say about Ketanji Brown Jackson\",\n",
@ -233,23 +204,9 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while youre at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, Id like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nations top legal minds, who will continue Justice Breyers legacy of excellence.\n"
]
}
],
"outputs": [],
"source": [
"# Perform a hybrid search\n",
"docs = vector_store.similarity_search(\n",
@ -262,23 +219,9 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while youre at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, Id like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nations top legal minds, who will continue Justice Breyers legacy of excellence.\n"
]
}
],
"outputs": [],
"source": [
"# Perform a hybrid search\n",
"docs = vector_store.hybrid_search(\n",
@ -296,7 +239,7 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -309,7 +252,12 @@
" TextWeights,\n",
")\n",
"\n",
"embeddings: OpenAIEmbeddings = OpenAIEmbeddings(deployment=model, chunk_size=1)\n",
"embeddings: AzureOpenAIEmbeddings = AzureOpenAIEmbeddings(\n",
" azure_deployment=\"text-embedding-ada-002\",\n",
" openai_api_version=\"2023-05-15\",\n",
" azure_endpoint=\"YOUR_AZURE_OPENAI_ENDPOINT\",\n",
" api_key=\"YOUR_AZURE_OPENAI_KEY\",\n",
")\n",
"embedding_function = embeddings.embed_query\n",
"\n",
"fields = [\n",
@ -329,7 +277,7 @@
" type=SearchFieldDataType.Collection(SearchFieldDataType.Single),\n",
" searchable=True,\n",
" vector_search_dimensions=len(embedding_function(\"Text\")),\n",
" vector_search_configuration=\"default\",\n",
" vector_search_profile_name=\"myHnswProfile\",\n",
" ),\n",
" SearchableField(\n",
" name=\"metadata\",\n",
@ -370,7 +318,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -390,22 +338,9 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Test 3', metadata={'title': 'Title 3', 'source': 'B', 'random': '32893'}),\n",
" Document(page_content='Test 1', metadata={'title': 'Title 1', 'source': 'A', 'random': '10290'}),\n",
" Document(page_content='Test 2', metadata={'title': 'Title 2', 'source': 'A', 'random': '48392'})]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"res = vector_store.similarity_search(query=\"Test 3 source1\", k=3, search_type=\"hybrid\")\n",
"res"
@ -413,21 +348,9 @@
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Test 1', metadata={'title': 'Title 1', 'source': 'A', 'random': '10290'}),\n",
" Document(page_content='Test 2', metadata={'title': 'Title 2', 'source': 'A', 'random': '48392'})]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"res = vector_store.similarity_search(\n",
" query=\"Test 3 source1\", k=3, search_type=\"hybrid\", filters=\"source eq 'A'\"\n",
@ -444,7 +367,7 @@
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -459,7 +382,12 @@
" TextWeights,\n",
")\n",
"\n",
"embeddings: OpenAIEmbeddings = OpenAIEmbeddings(deployment=model, chunk_size=1)\n",
"embeddings: AzureOpenAIEmbeddings = AzureOpenAIEmbeddings(\n",
" azure_deployment=\"text-embedding-ada-002\",\n",
" openai_api_version=\"2023-05-15\",\n",
" azure_endpoint=\"YOUR_AZURE_OPENAI_ENDPOINT\",\n",
" api_key=\"YOUR_AZURE_OPENAI_KEY\",\n",
")\n",
"embedding_function = embeddings.embed_query\n",
"\n",
"fields = [\n",
@ -479,7 +407,7 @@
" type=SearchFieldDataType.Collection(SearchFieldDataType.Single),\n",
" searchable=True,\n",
" vector_search_dimensions=len(embedding_function(\"Text\")),\n",
" vector_search_configuration=\"default\",\n",
" vector_search_profile_name=\"myHnswProfile\",\n",
" ),\n",
" SearchableField(\n",
" name=\"metadata\",\n",
@ -537,22 +465,9 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['NjQyNTI5ZmMtNmVkYS00Njg5LTk2ZDgtMjM3OTY4NTJkYzFj',\n",
" 'M2M0MGExZjAtMjhiZC00ZDkwLThmMTgtODNlN2Y2ZDVkMTMw',\n",
" 'ZmFhMDE1NzMtMjZjNS00MTFiLTk0MTEtNGRkYjgwYWQwOTI0']"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"# Adding same data with different last_update to show Scoring Profile effect\n",
"from datetime import datetime, timedelta\n",
@ -590,33 +505,13 @@
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Test 1', metadata={'title': 'Title 1', 'source': 'source1', 'random': '10290', 'last_update': '2023-07-13T10:47:39-00:00'}),\n",
" Document(page_content='Test 1', metadata={'title': 'Title 1', 'source': 'source1', 'random': '48392', 'last_update': '2023-07-12T10:47:39-00:00'}),\n",
" Document(page_content='Test 1', metadata={'title': 'Title 1', 'source': 'source1', 'random': '32893', 'last_update': '2023-06-13T10:47:39-00:00'})]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"res = vector_store.similarity_search(query=\"Test 1\", k=3, search_type=\"similarity\")\n",
"res"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -635,7 +530,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
"version": "3.11.7"
},
"orig_nbformat": 4,
"vscode": {

Loading…
Cancel
Save