github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-07 14:03:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/add to imports (#7370)

Browse Source 
pgvector cleanup
This commit is contained in:
Harrison Chase
2023-07-07 16:27:44 -04:00
committed by GitHub
parent 4d427b2397
commit 7cdf97ba9b
4 changed files with 278 additions and 252 deletions
Download Patch File Download Diff File Expand all files Collapse all files

363
docs/extras/modules/data_connection/vectorstores/integrations/pgvector.ipynb
View File

@@ -123,7 +123,7 @@
},
{
"cell_type": "code",
"execution_count": 62,
"execution_count": 1,
"metadata": {
"tags": []
},
@@ -138,7 +138,7 @@
},
{
"cell_type": "code",
"execution_count": 63,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@@ -152,49 +152,25 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"## PGVector needs the connection string to the database.\n",
"## We will load it from the environment variables.\n",
"import os\n",
"# PGVector needs the connection string to the database.\n",
"CONNECTION_STRING = \"postgresql+psycopg2://harrisonchase@localhost:5432/test3\"\n",
"\n",
"CONNECTION_STRING = PGVector.connection_string_from_db_params(\n",
" driver=os.environ.get(\"PGVECTOR_DRIVER\", \"psycopg2\"),\n",
" host=os.environ.get(\"PGVECTOR_HOST\", \"localhost\"),\n",
" port=int(os.environ.get(\"PGVECTOR_PORT\", \"5432\")),\n",
" database=os.environ.get(\"PGVECTOR_DATABASE\", \"postgres\"),\n",
" user=os.environ.get(\"PGVECTOR_USER\", \"postgres\"),\n",
" password=os.environ.get(\"PGVECTOR_PASSWORD\", \"postgres\"),\n",
")\n",
"\n",
"\n",
"## Example\n",
"# postgresql+psycopg2://username:password@localhost:5432/database_name"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [],
"source": [
"# ## PGVector needs the connection string to the database.\n",
"# ## We will load it from the environment variables.\n",
"# # Alternatively, you can create it from enviornment variables.\n",
"# import os\n",
"\n",
"# CONNECTION_STRING = PGVector.connection_string_from_db_params(\n",
"# driver=os.environ.get(\"PGVECTOR_DRIVER\", \"psycopg2\"),\n",
"# host=os.environ.get(\"PGVECTOR_HOST\", \"localhost\"),\n",
"# port=int(os.environ.get(\"PGVECTOR_PORT\", \"5432\")),\n",
"# database=os.environ.get(\"PGVECTOR_DATABASE\", \"rd-embeddings\"),\n",
"# user=os.environ.get(\"PGVECTOR_USER\", \"admin\"),\n",
"# password=os.environ.get(\"PGVECTOR_PASSWORD\", \"password\"),\n",
"# database=os.environ.get(\"PGVECTOR_DATABASE\", \"postgres\"),\n",
"# user=os.environ.get(\"PGVECTOR_USER\", \"postgres\"),\n",
"# password=os.environ.get(\"PGVECTOR_PASSWORD\", \"postgres\"),\n",
"# )\n",
"\n",
"\n",
"# ## Example\n",
"# # postgresql+psycopg2://username:password@localhost:5432/database_name"
"\n"
]
},
{
@@ -206,27 +182,36 @@
},
{
"cell_type": "code",
"execution_count": 69,
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"# The PGVector Module will try to create a table with the name of the collection. So, make sure that the collection name is unique and the user has the\n",
"# permission to create a table.\n",
"# The PGVector Module will try to create a table with the name of the collection. \n",
"# So, make sure that the collection name is unique and the user has the permission to create a table.\n",
"\n",
"COLLECTION_NAME = \"state_of_the_union_test\"\n",
"\n",
"db = PGVector.from_documents(\n",
" embedding=embeddings,\n",
" documents=docs,\n",
" collection_name=\"state_of_the_union\",\n",
" collection_name=COLLECTION_NAME,\n",
" connection_string=CONNECTION_STRING,\n",
")\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs_with_score: List[Tuple[Document, float]] = db.similarity_search_with_score(query)"
")"
]
},
{
"cell_type": "code",
"execution_count": 70,
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs_with_score = db.similarity_search_with_score(query)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -234,7 +219,7 @@
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"Score: 0.6076804864602984\n",
"Score: 0.18460171628856903\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d 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",
@@ -244,7 +229,7 @@
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
"--------------------------------------------------------------------------------\n",
"--------------------------------------------------------------------------------\n",
"Score: 0.6076804864602984\n",
"Score: 0.18460171628856903\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d 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",
@@ -254,21 +239,17 @@
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
"--------------------------------------------------------------------------------\n",
"--------------------------------------------------------------------------------\n",
"Score: 0.659062774389974\n",
"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 she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
"Score: 0.18470284560586236\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
"Tonight, I’d 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",
"We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \n",
"\n",
"We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
"\n",
"We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
"--------------------------------------------------------------------------------\n",
"--------------------------------------------------------------------------------\n",
"Score: 0.659062774389974\n",
"Score: 0.21730864082247825\n",
"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 she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
"\n",
"And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
@@ -296,183 +277,189 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Working with vectorstore"
"## Working with vectorstore\n",
"\n",
"Above, we created a vectorstore from scratch. However, often times we want to work with an existing vectorstore.\n",
"In order to do that, we can initialize it directly."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"store = PGVector(\n",
" collection_name=COLLECTION_NAME,\n",
" connection_string=CONNECTION_STRING,\n",
" embedding_function=embeddings,\n",
")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Uploading a vectorstore"
"### Add documents\n",
"We can add documents to the existing vectorstore."
]
},
{
"cell_type": "code",
"execution_count": 55,
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['048c2e14-1cf3-11ee-8777-e65801318980']"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"store.add_documents([Document(page_content=\"foo\")])"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"docs_with_score = db.similarity_search_with_score(\"foo\")"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(Document(page_content='foo', metadata={}), 3.3203430005457335e-09)"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs_with_score[0]"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(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 she’s been nominated, she’s 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, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt'}),\n",
" 0.2404395365581814)"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs_with_score[1]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Overriding a vectorstore\n",
"\n",
"If you have an existing collection, you override it by doing `from_documents` and setting `pre_delete_collection` = True"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"data = docs\n",
"api_key = os.environ[\"OPENAI_API_KEY\"]\n",
"db = PGVector.from_documents(\n",
" documents=docs,\n",
" embedding=embeddings,\n",
" collection_name=collection_name,\n",
" connection_string=connection_string,\n",
" distance_strategy=DistanceStrategy.COSINE,\n",
" openai_api_key=api_key,\n",
" pre_delete_collection=False,\n",
" collection_name=COLLECTION_NAME,\n",
" connection_string=CONNECTION_STRING,\n",
" pre_delete_collection=True,\n",
")"
]
},
{
"cell_type": "markdown",
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"### Retrieving a vectorstore"
"docs_with_score = db.similarity_search_with_score(\"foo\")"
]
},
{
"cell_type": "code",
"execution_count": 56,
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(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 she’s been nominated, she’s 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, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt'}),\n",
" 0.2404115088144465)"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs_with_score[0]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Using a VectorStore as a Retriever"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"connection_string = CONNECTION_STRING\n",
"embedding = embeddings\n",
"collection_name = \"state_of_the_union\"\n",
"from langchain.vectorstores.pgvector import DistanceStrategy\n",
"\n",
"store = PGVector(\n",
" connection_string=connection_string,\n",
" embedding_function=embedding,\n",
" collection_name=collection_name,\n",
" distance_strategy=DistanceStrategy.COSINE,\n",
")\n",
"\n",
"retriever = store.as_retriever()"
]
},
{
"cell_type": "code",
"execution_count": 57,
"execution_count": 27,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"vectorstore=<langchain.vectorstores.pgvector.PGVector object at 0x7fe9a1b1c670> search_type='similarity' search_kwargs={}\n"
"tags=None metadata=None vectorstore=<langchain.vectorstores.pgvector.PGVector object at 0x29f94f880> search_type='similarity' search_kwargs={}\n"
]
}
],
"source": [
"print(retriever)"
]
},
{
"cell_type": "code",
"execution_count": 83,
"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 you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d 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 nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6075870262188066), (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 you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d 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 nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6075870262188066), (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 she’s been nominated, she’s 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, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6589478388546668), (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 she’s been nominated, she’s 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, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6589478388546668)]\n"
]
}
],
"source": [
"# When we have an existing PG VEctor\n",
"DEFAULT_DISTANCE_STRATEGY = DistanceStrategy.EUCLIDEAN\n",
"db1 = PGVector.from_existing_index(\n",
" embedding=embeddings,\n",
" collection_name=\"state_of_the_union\",\n",
" distance_strategy=DEFAULT_DISTANCE_STRATEGY,\n",
" pre_delete_collection=False,\n",
" connection_string=CONNECTION_STRING,\n",
")\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs_with_score: List[Tuple[Document, float]] = db1.similarity_search_with_score(query)\n",
"print(docs_with_score)"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"Score: 0.6075870262188066\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d 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 nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
"--------------------------------------------------------------------------------\n",
"--------------------------------------------------------------------------------\n",
"Score: 0.6075870262188066\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d 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 nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
"--------------------------------------------------------------------------------\n",
"--------------------------------------------------------------------------------\n",
"Score: 0.6589478388546668\n",
"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 she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
"\n",
"And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
"\n",
"We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \n",
"\n",
"We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \n",
"\n",
"We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
"\n",
"We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
"--------------------------------------------------------------------------------\n",
"--------------------------------------------------------------------------------\n",
"Score: 0.6589478388546668\n",
"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 she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
"\n",
"And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
"\n",
"We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \n",
"\n",
"We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \n",
"\n",
"We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
"\n",
"We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
"--------------------------------------------------------------------------------\n"
]
}
],
"source": [
"for doc, score in docs_with_score:\n",
" print(\"-\" * 80)\n",
" print(\"Score: \", score)\n",
" print(doc.page_content)\n",
" print(\"-\" * 80)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@@ -491,7 +478,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
"version": "3.9.1"
}
},
"nbformat": 4,