diff --git a/docs/modules/indexes/vectorstores/examples/pgvector.ipynb b/docs/modules/indexes/vectorstores/examples/pgvector.ipynb index 314e7f64d3..ff0fabf0a0 100644 --- a/docs/modules/indexes/vectorstores/examples/pgvector.ipynb +++ b/docs/modules/indexes/vectorstores/examples/pgvector.ipynb @@ -24,13 +24,48 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 60, "metadata": { "tags": [] }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pgvector in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.1.8)\n", + "Requirement already satisfied: numpy in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from pgvector) (1.24.3)\n", + "Requirement already satisfied: openai in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.27.7)\n", + "Requirement already satisfied: requests>=2.20 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (2.28.2)\n", + "Requirement already satisfied: tqdm in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (4.65.0)\n", + "Requirement already satisfied: aiohttp in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (3.8.4)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (3.1.0)\n", + "Requirement already satisfied: idna<4,>=2.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (3.4)\n", + "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (1.26.15)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (2023.5.7)\n", + "Requirement already satisfied: attrs>=17.3.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (23.1.0)\n", + "Requirement already satisfied: multidict<7.0,>=4.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (6.0.4)\n", + "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (4.0.2)\n", + "Requirement already satisfied: yarl<2.0,>=1.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.9.2)\n", + "Requirement already satisfied: frozenlist>=1.1.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.3.3)\n", + "Requirement already satisfied: aiosignal>=1.1.2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.3.1)\n", + "Requirement already satisfied: psycopg2-binary in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (2.9.6)\n", + "Requirement already satisfied: tiktoken in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.4.0)\n", + "Requirement already satisfied: regex>=2022.1.18 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from tiktoken) (2023.5.5)\n", + "Requirement already satisfied: requests>=2.26.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from tiktoken) (2.28.2)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (3.1.0)\n", + "Requirement already satisfied: idna<4,>=2.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (3.4)\n", + "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (1.26.15)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (2023.5.7)\n" + ] + } + ], "source": [ - "!pip install pgvector" + "# Pip install necessary package\n", + "!pip install pgvector\n", + "!pip install openai\n", + "!pip install psycopg2-binary\n", + "!pip install tiktoken" ] }, { @@ -42,9 +77,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "OpenAI API Key:········\n" + ] + } + ], "source": [ "import os\n", "import getpass\n", @@ -54,7 +97,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 61, "metadata": { "tags": [] }, @@ -65,7 +108,7 @@ "False" ] }, - "execution_count": 1, + "execution_count": 61, "metadata": {}, "output_type": "execute_result" } @@ -79,7 +122,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 62, "metadata": { "tags": [] }, @@ -94,7 +137,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 63, "metadata": {}, "outputs": [], "source": [ @@ -129,6 +172,29 @@ "# 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", + "# import os\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", + "# )\n", + "\n", + "\n", + "# ## Example\n", + "# # postgresql+psycopg2://username:password@localhost:5432/database_name" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -145,7 +211,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 69, "metadata": {}, "outputs": [], "source": [ @@ -165,7 +231,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 70, "metadata": {}, "outputs": [ { @@ -173,7 +239,7 @@ "output_type": "stream", "text": [ "--------------------------------------------------------------------------------\n", - "Score: 0.6076628081132506\n", + "Score: 0.6076804864602984\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", @@ -183,7 +249,7 @@ "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: 0.6076628081132506\n", + "Score: 0.6076804864602984\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", @@ -193,24 +259,32 @@ "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: 0.6076804780049968\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", + "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", "\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", + "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n", "\n", - "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n", + "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \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", + "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: 0.6076804780049968\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", + "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", "\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", + "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n", "\n", - "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n", + "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \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", + "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" ] } @@ -224,7 +298,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ @@ -232,7 +305,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ @@ -241,10 +313,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "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", @@ -257,7 +331,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ @@ -266,10 +339,14 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 56, "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", "store = PGVector(\n", " connection_string=connection_string, \n", " embedding_function=embedding, \n", @@ -279,6 +356,127 @@ "\n", "retriever = store.as_retriever()" ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "vectorstore= 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": { @@ -297,7 +495,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.6" + "version": "3.9.7" } }, "nbformat": 4, diff --git a/langchain/embeddings/cohere.py b/langchain/embeddings/cohere.py index a107dc02cc..e4fe18b247 100644 --- a/langchain/embeddings/cohere.py +++ b/langchain/embeddings/cohere.py @@ -48,7 +48,7 @@ class CohereEmbeddings(BaseModel, Embeddings): values["client"] = cohere.Client(cohere_api_key) except ImportError: - raise ImportError( + raise ValueError( "Could not import cohere python package. " "Please install it with `pip install cohere`." ) diff --git a/langchain/vectorstores/pgvector.py b/langchain/vectorstores/pgvector.py index 161e8e2c52..0e99f50071 100644 --- a/langchain/vectorstores/pgvector.py +++ b/langchain/vectorstores/pgvector.py @@ -505,6 +505,33 @@ class PGVector(VectorStore): **kwargs, ) + @classmethod + def from_existing_index( + cls: Type[PGVector], + embedding: Embeddings, + collection_name: str = _LANGCHAIN_DEFAULT_COLLECTION_NAME, + distance_strategy: DistanceStrategy = DistanceStrategy.COSINE, + pre_delete_collection: bool = False, + **kwargs: Any, + ) -> PGVector: + """ + Get intsance of an existing PGVector store.This method will + return the instance of the store without inserting any new + embeddings + """ + + connection_string = cls.get_connection_string(kwargs) + + store = cls( + connection_string=connection_string, + collection_name=collection_name, + embedding_function=embedding, + distance_strategy=distance_strategy, + pre_delete_collection=pre_delete_collection, + ) + + return store + @classmethod def get_connection_string(cls, kwargs: Dict[str, Any]) -> str: connection_string: str = get_from_dict_or_env(