diff --git a/docs/docs/how_to/embed_text.mdx b/docs/docs/how_to/embed_text.mdx index 2450e99440c..0c636fec3e7 100644 --- a/docs/docs/how_to/embed_text.mdx +++ b/docs/docs/how_to/embed_text.mdx @@ -15,87 +15,9 @@ The base Embeddings class in LangChain provides two methods: one for embedding d ### Setup -import Tabs from '@theme/Tabs'; -import TabItem from '@theme/TabItem'; +import EmbeddingTabs from "@theme/EmbeddingTabs"; - - -To start we'll need to install the OpenAI partner package: - -```bash -pip install langchain-openai -``` - -Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable by running: - -```bash -export OPENAI_API_KEY="..." -``` - -If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the OpenAI LLM class: - -```python -from langchain_openai import OpenAIEmbeddings - -embeddings_model = OpenAIEmbeddings(api_key="...") -``` - -Otherwise you can initialize without any params: -```python -from langchain_openai import OpenAIEmbeddings - -embeddings_model = OpenAIEmbeddings() -``` - - - - -To start we'll need to install the Cohere SDK package: - -```bash -pip install langchain-cohere -``` - -Accessing the API requires an API key, which you can get by creating an account and heading [here](https://dashboard.cohere.com/api-keys). Once we have a key we'll want to set it as an environment variable by running: - -```shell -export COHERE_API_KEY="..." -``` - -If you'd prefer not to set an environment variable you can pass the key in directly via the `cohere_api_key` named parameter when initiating the Cohere LLM class: - -```python -from langchain_cohere import CohereEmbeddings - -embeddings_model = CohereEmbeddings(cohere_api_key="...", model='embed-english-v3.0') -``` - -Otherwise you can initialize simply as shown below: -```python -from langchain_cohere import CohereEmbeddings - -embeddings_model = CohereEmbeddings(model='embed-english-v3.0') -``` -Do note that it is mandatory to pass the model parameter while initializing the CohereEmbeddings class. - - - - -To start we'll need to install the Hugging Face partner package: - -```bash -pip install langchain-huggingface -``` - -You can then load any [Sentence Transformers model](https://huggingface.co/models?library=sentence-transformers) from the Hugging Face Hub. - -```python -from langchain_huggingface import HuggingFaceEmbeddings - -embeddings_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") -``` - - + ### `embed_documents` #### Embed list of texts diff --git a/docs/docs/integrations/chat/index.mdx b/docs/docs/integrations/chat/index.mdx index e2b0be6da4d..537cdc2c11a 100644 --- a/docs/docs/integrations/chat/index.mdx +++ b/docs/docs/integrations/chat/index.mdx @@ -15,6 +15,14 @@ If you'd like to contribute an integration, see [Contributing integrations](/doc ::: +import ChatModelTabs from "@theme/ChatModelTabs"; + + + +```python +model.invoke("Hello, world!") +``` + ## Featured Providers :::info diff --git a/docs/docs/integrations/text_embedding/azureopenai.ipynb b/docs/docs/integrations/text_embedding/azureopenai.ipynb index 7f5281e21e9..916132c6f3e 100644 --- a/docs/docs/integrations/text_embedding/azureopenai.ipynb +++ b/docs/docs/integrations/text_embedding/azureopenai.ipynb @@ -45,7 +45,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "id": "36521c2a", "metadata": {}, "outputs": [], @@ -53,8 +53,10 @@ "import getpass\n", "import os\n", "\n", - "if not os.getenv(\"OPENAI_API_KEY\"):\n", - " os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter your AzureOpenAI API key: \")" + "if not os.getenv(\"AZURE_OPENAI_API_KEY\"):\n", + " os.environ[\"AZURE_OPENAI_API_KEY\"] = getpass.getpass(\n", + " \"Enter your AzureOpenAI API key: \"\n", + " )" ] }, { diff --git a/docs/docs/integrations/text_embedding/bedrock.ipynb b/docs/docs/integrations/text_embedding/bedrock.ipynb index 3c476850782..b559621f291 100644 --- a/docs/docs/integrations/text_embedding/bedrock.ipynb +++ b/docs/docs/integrations/text_embedding/bedrock.ipynb @@ -31,12 +31,12 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "id": "282239c8-e03a-4abc-86c1-ca6120231a20", "metadata": {}, "outputs": [], "source": [ - "from langchain_community.embeddings import BedrockEmbeddings\n", + "from langchain_aws import BedrockEmbeddings\n", "\n", "embeddings = BedrockEmbeddings(\n", " credentials_profile_name=\"bedrock-admin\", region_name=\"us-east-1\"\n", diff --git a/docs/docs/integrations/text_embedding/index.mdx b/docs/docs/integrations/text_embedding/index.mdx index fe2a6271921..16948056512 100644 --- a/docs/docs/integrations/text_embedding/index.mdx +++ b/docs/docs/integrations/text_embedding/index.mdx @@ -11,6 +11,14 @@ import { CategoryTable, IndexTable } from "@theme/FeatureTables"; This page documents integrations with various model providers that allow you to use embeddings in LangChain. +import EmbeddingTabs from "@theme/EmbeddingTabs"; + + + +```python +embeddings.embed_query("Hello, world!") +``` + ## All embedding models diff --git a/docs/docs/integrations/vectorstores/index.mdx b/docs/docs/integrations/vectorstores/index.mdx index 8b276057dad..c213d968ee3 100644 --- a/docs/docs/integrations/vectorstores/index.mdx +++ b/docs/docs/integrations/vectorstores/index.mdx @@ -3,12 +3,24 @@ sidebar_position: 0 sidebar_class_name: hidden --- -# Vectorstores +# Vector stores import { CategoryTable, IndexTable } from "@theme/FeatureTables"; A [vector store](/docs/concepts/vectorstores) stores [embedded](/docs/concepts/embedding_models) data and performs similarity search. +**Select embedding model:** + +import EmbeddingTabs from "@theme/EmbeddingTabs"; + + + +**Select vector store:** + +import VectorStoreTabs from "@theme/VectorStoreTabs"; + + + ## All Vectorstores diff --git a/docs/src/theme/ChatModelTabs.js b/docs/src/theme/ChatModelTabs.js index 9d27a9a44a1..162723942aa 100644 --- a/docs/src/theme/ChatModelTabs.js +++ b/docs/src/theme/ChatModelTabs.js @@ -114,7 +114,7 @@ export default function ChatModelTabs(props) { value: "Google", label: "Google", text: `from langchain_google_vertexai import ChatVertexAI\n\n${llmVarName} = ChatVertexAI(${googleParamsOrDefault})`, - apiKeyName: "GOOGLE_API_KEY", + apiKeyText: "# Ensure your VertexAI credentials are configured", packageName: "langchain-google-vertexai", default: false, shouldHide: hideGoogle, diff --git a/docs/src/theme/EmbeddingTabs.js b/docs/src/theme/EmbeddingTabs.js index 7ad62a515ad..3c4d1d814fd 100644 --- a/docs/src/theme/EmbeddingTabs.js +++ b/docs/src/theme/EmbeddingTabs.js @@ -7,15 +7,41 @@ export default function EmbeddingTabs(props) { const { openaiParams, hideOpenai, + azureOpenaiParams, + hideAzureOpenai, + googleParams, + hideGoogle, + awsParams, + hideAws, huggingFaceParams, hideHuggingFace, + ollamaParams, + hideOllama, + cohereParams, + hideCohere, + mistralParams, + hideMistral, + nomicParams, + hideNomic, + nvidiaParams, + hideNvidia, fakeEmbeddingParams, hideFakeEmbedding, customVarName, } = props; const openAIParamsOrDefault = openaiParams ?? `model="text-embedding-3-large"`; + const azureParamsOrDefault = + azureOpenaiParams ?? + `\n azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],\n azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],\n openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],\n`; + const googleParamsOrDefault = googleParams ?? `model="text-embedding-004"`; + const awsParamsOrDefault = awsParams ?? `model_id="amazon.titan-embed-text-v2:0"`; const huggingFaceParamsOrDefault = huggingFaceParams ?? `model="sentence-transformers/all-mpnet-base-v2"`; + const ollamaParamsOrDefault = ollamaParams ?? `model="llama3"`; + const cohereParamsOrDefault = cohereParams ?? `model="embed-english-v3.0"`; + const mistralParamsOrDefault = mistralParams ?? `model="mistral-embed"`; + const nomicsParamsOrDefault = nomicParams ?? `model="nomic-embed-text-v1.5"`; + const nvidiaParamsOrDefault = nvidiaParams ?? `model="NV-Embed-QA"`; const fakeEmbeddingParamsOrDefault = fakeEmbeddingParams ?? `size=4096`; const embeddingVarName = customVarName ?? "embeddings"; @@ -30,6 +56,33 @@ export default function EmbeddingTabs(props) { default: true, shouldHide: hideOpenai, }, + { + value: "Azure", + label: "Azure", + text: `from langchain_openai import AzureOpenAIEmbeddings\n\n${embeddingVarName} = AzureOpenAIEmbeddings(${azureParamsOrDefault})`, + apiKeyName: "AZURE_OPENAI_API_KEY", + packageName: "langchain-openai", + default: false, + shouldHide: hideAzureOpenai, + }, + { + value: "Google", + label: "Google", + text: `from langchain_google_vertexai import VertexAIEmbeddings\n\n${embeddingVarName} = VertexAIEmbeddings(${googleParamsOrDefault})`, + apiKeyName: undefined, + packageName: "langchain-google-vertexai", + default: false, + shouldHide: hideGoogle, + }, + { + value: "AWS", + label: "AWS", + text: `from langchain_aws import BedrockEmbeddings\n\n${embeddingVarName} = BedrockEmbeddings(${awsParamsOrDefault})`, + apiKeyName: undefined, + packageName: "langchain-aws", + default: false, + shouldHide: hideAws, + }, { value: "HuggingFace", label: "HuggingFace", @@ -40,8 +93,53 @@ export default function EmbeddingTabs(props) { shouldHide: hideHuggingFace, }, { - value: "Fake Embedding", - label: "Fake Embedding", + value: "Ollama", + label: "Ollama", + text: `from langchain_ollama import OllamaEmbeddings\n\n${embeddingVarName} = OllamaEmbeddings(${ollamaParamsOrDefault})`, + apiKeyName: undefined, + packageName: "langchain-ollama", + default: false, + shouldHide: hideOllama, + }, + { + value: "Cohere", + label: "Cohere", + text: `from langchain_cohere import CohereEmbeddings\n\n${embeddingVarName} = CohereEmbeddings(${cohereParamsOrDefault})`, + apiKeyName: "COHERE_API_KEY", + packageName: "langchain-cohere", + default: false, + shouldHide: hideCohere, + }, + { + value: "MistralAI", + label: "MistralAI", + text: `from langchain_mistralai import MistralAIEmbeddings\n\n${embeddingVarName} = MistralAIEmbeddings(${mistralParamsOrDefault})`, + apiKeyName: "MISTRALAI_API_KEY", + packageName: "langchain-mistralai", + default: false, + shouldHide: hideMistral, + }, + { + value: "Nomic", + label: "Nomic", + text: `from langchain_nomic import NomicEmbeddings\n\n${embeddingVarName} = NomicEmbeddings(${nomicsParamsOrDefault})`, + apiKeyName: "NOMIC_API_KEY", + packageName: "langchain-nomic", + default: false, + shouldHide: hideNomic, + }, + { + value: "NVIDIA", + label: "NVIDIA", + text: `from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings\n\n${embeddingVarName} = NVIDIAEmbeddings(${nvidiaParamsOrDefault})`, + apiKeyName: "NVIDIA_API_KEY", + packageName: "langchain-nvidia-ai-endpoints", + default: false, + shouldHide: hideNvidia, + }, + { + value: "Fake", + label: "Fake", text: `from langchain_core.embeddings import FakeEmbeddings\n\n${embeddingVarName} = FakeEmbeddings(${fakeEmbeddingParamsOrDefault})`, apiKeyName: undefined, packageName: "langchain-core", diff --git a/docs/src/theme/FeatureTables.js b/docs/src/theme/FeatureTables.js index a7b31cdc291..afa27742aae 100644 --- a/docs/src/theme/FeatureTables.js +++ b/docs/src/theme/FeatureTables.js @@ -406,7 +406,7 @@ const FEATURE_TABLES = { }, { name: "NVIDIA", - link: "NVIDIAEmbeddings", + link: "nvidia_ai_endpoints", package: "langchain-nvidia", apiLink: "https://python.langchain.com/api_reference/nvidia_ai_endpoints/embeddings/langchain_nvidia_ai_endpoints.embeddings.NVIDIAEmbeddings.html" }, diff --git a/docs/src/theme/VectorStoreTabs.js b/docs/src/theme/VectorStoreTabs.js new file mode 100644 index 00000000000..52c20fba515 --- /dev/null +++ b/docs/src/theme/VectorStoreTabs.js @@ -0,0 +1,92 @@ +import React from "react"; +import Tabs from "@theme/Tabs"; +import TabItem from "@theme/TabItem"; +import CodeBlock from "@theme-original/CodeBlock"; + +export default function VectorStoreTabs(props) { + const { customVarName } = props; + + const vectorStoreVarName = customVarName ?? "vector_store"; + + const tabItems = [ + { + value: "In-memory", + label: "In-memory", + text: `from langchain_core.vector_stores import InMemoryVectorStore\n\n${vectorStoreVarName} = InMemoryVectorStore(embeddings)`, + packageName: "langchain-core", + default: true, + }, + { + value: "AstraDB", + label: "AstraDB", + text: `from langchain_astradb import AstraDBVectorStore\n\n${vectorStoreVarName} = AstraDBVectorStore(\n embedding=embeddings,\n api_endpoint=ASTRA_DB_API_ENDPOINT,\n collection_name="astra_vector_langchain",\n token=ASTRA_DB_APPLICATION_TOKEN,\n namespace=ASTRA_DB_NAMESPACE,\n)`, + packageName: "langchain-astradb", + default: false, + }, + { + value: "Chroma", + label: "Chroma", + text: `from langchain_chroma import Chroma\n\n${vectorStoreVarName} = Chroma(embedding_function=embeddings)`, + packageName: "langchain-chroma", + default: false, + }, + { + value: "FAISS", + label: "FAISS", + text: `from langchain_community.vectorstores import FAISS\n\n${vectorStoreVarName} = FAISS(embedding_function=embeddings)`, + packageName: "langchain-community", + default: false, + }, + { + value: "Milvus", + label: "Milvus", + text: `from langchain_milvus import Milvus\n\n${vectorStoreVarName} = Milvus(embedding_function=embeddings)`, + packageName: "langchain-milvus", + default: false, + }, + { + value: "MongoDB", + label: "MongoDB", + text: `from langchain_mongodb import MongoDBAtlasVectorSearch\n\n${vectorStoreVarName} = MongoDBAtlasVectorSearch(\n embedding=embeddings,\n collection=MONGODB_COLLECTION,\n index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n relevance_score_fn="cosine",\n)`, + packageName: "langchain-mongodb", + default: false, + }, + { + value: "PGVector", + label: "PGVector", + text: `from langchain_postgres import PGVector\n\n${vectorStoreVarName} = PGVector(\n embedding=embeddings,\n collection_name="my_docs",\n connection="postgresql+psycopg://...",\n)`, + packageName: "langchain-postgres", + default: false, + }, + { + value: "Pinecone", + label: "Pinecone", + text: `from langchain_pinecone import PineconeVectorStore\nfrom pinecone import Pinecone\n\npc = Pinecone(api_key=...)\nindex = pc.Index(index_name)\n\n${vectorStoreVarName} = PineconeVectorStore(embedding=embeddings, index=index)`, + packageName: "langchain-pinecone", + default: false, + }, + { + value: "Qdrant", + label: "Qdrant", + text: `from langchain_qdrant import QdrantVectorStore\nfrom qdrant_client import QdrantClient\n\nclient = QdrantClient(":memory:")\n${vectorStoreVarName} = QdrantVectorStore(\n client=client,\n collection_name="test",\n embedding=embeddings,\n)`, + packageName: "langchain-qdrant", + default: false, + }, + ]; + + return ( + + {tabItems.map((tabItem) => ( + + {`pip install -qU ${tabItem.packageName}`} + {tabItem.text} + + ))} + + ); +}