使用 LangChain 构建语义搜索引擎

pip install -U "langchain-openai"

import getpass
import os

if not os.environ.get("AZURE_OPENAI_API_KEY"):
os.environ["AZURE_OPENAI_API_KEY"] = getpass.getpass("Enter API key for Azure: ")

from langchain_openai import AzureOpenAIEmbeddings

embeddings = AzureOpenAIEmbeddings(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)

pip install -qU langchain-google-genai

import getpass
import os

if not os.environ.get("GOOGLE_API_KEY"):
os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter API key for Google Gemini: ")

from langchain_google_genai import GoogleGenerativeAIEmbeddings

embeddings = GoogleGenerativeAIEmbeddings(model="models/gemini-embedding-001")

pip install -qU langchain-google-vertexai

from langchain_google_vertexai import VertexAIEmbeddings

embeddings = VertexAIEmbeddings(model="text-embedding-005")

pip install -qU langchain-aws

from langchain_aws import BedrockEmbeddings

embeddings = BedrockEmbeddings(model_id="amazon.titan-embed-text-v2:0")

pip install -qU langchain-huggingface

from langchain_huggingface import HuggingFaceEmbeddings

embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="llama3")

pip install -qU langchain-cohere

import getpass
import os

if not os.environ.get("COHERE_API_KEY"):
os.environ["COHERE_API_KEY"] = getpass.getpass("Enter API key for Cohere: ")

from langchain_cohere import CohereEmbeddings

embeddings = CohereEmbeddings(model="embed-english-v3.0")

pip install -qU langchain-mistralai

import getpass
import os

if not os.environ.get("MISTRALAI_API_KEY"):
os.environ["MISTRALAI_API_KEY"] = getpass.getpass("Enter API key for MistralAI: ")

from langchain_mistralai import MistralAIEmbeddings

embeddings = MistralAIEmbeddings(model="mistral-embed")

pip install -qU langchain-nomic

import getpass
import os

if not os.environ.get("NOMIC_API_KEY"):
os.environ["NOMIC_API_KEY"] = getpass.getpass("Enter API key for Nomic: ")

from langchain_nomic import NomicEmbeddings

embeddings = NomicEmbeddings(model="nomic-embed-text-v1.5")

pip install -qU langchain-nvidia-ai-endpoints

import getpass
import os

if not os.environ.get("NVIDIA_API_KEY"):
os.environ["NVIDIA_API_KEY"] = getpass.getpass("Enter API key for NVIDIA: ")

from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings

embeddings = NVIDIAEmbeddings(model="NV-Embed-QA")

pip install -qU langchain-voyageai

import getpass
import os

if not os.environ.get("VOYAGE_API_KEY"):
os.environ["VOYAGE_API_KEY"] = getpass.getpass("Enter API key for Voyage AI: ")

from langchain-voyageai import VoyageAIEmbeddings

embeddings = VoyageAIEmbeddings(model="voyage-3")

pip install -qU langchain-ibm

import getpass
import os

if not os.environ.get("WATSONX_APIKEY"):
os.environ["WATSONX_APIKEY"] = getpass.getpass("Enter API key for IBM watsonx: ")

from langchain_ibm import WatsonxEmbeddings

embeddings = WatsonxEmbeddings(
    model_id="ibm/slate-125m-english-rtrvr",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="<WATSONX PROJECT_ID>",
)

pip install -qU langchain-core

from langchain_core.embeddings import DeterministicFakeEmbedding

embeddings = DeterministicFakeEmbedding(size=4096)

pip install -U "langchain-astradb"

from langchain_astradb import AstraDBVectorStore

vector_store = AstraDBVectorStore(
    embedding=embeddings,
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    collection_name="astra_vector_langchain",
    token=ASTRA_DB_APPLICATION_TOKEN,
    namespace=ASTRA_DB_NAMESPACE,
)

pip install -qU langchain-chroma

from langchain_chroma import Chroma

vector_store = Chroma(
    collection_name="example_collection",
    embedding_function=embeddings,
    persist_directory="./chroma_langchain_db",  # Where to save data locally, remove if not necessary
)

pip install -qU langchain-community

import faiss
from langchain_community.docstore.in_memory import InMemoryDocstore
from langchain_community.vectorstores import FAISS

embedding_dim = len(embeddings.embed_query("hello world"))
index = faiss.IndexFlatL2(embedding_dim)

vector_store = FAISS(
    embedding_function=embeddings,
    index=index,
    docstore=InMemoryDocstore(),
    index_to_docstore_id={},
)

pip install -qU langchain-milvus

from langchain_milvus import Milvus

URI = "./milvus_example.db"

vector_store = Milvus(
    embedding_function=embeddings,
    connection_args={"uri": URI},
    index_params={"index_type": "FLAT", "metric_type": "L2"},
)

pip install -qU langchain-mongodb

from langchain_mongodb import MongoDBAtlasVectorSearch

vector_store = MongoDBAtlasVectorSearch(
    embedding=embeddings,
    collection=MONGODB_COLLECTION,
    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
    relevance_score_fn="cosine",
)

pip install -qU langchain-postgres

from langchain_postgres import PGVector

vector_store = PGVector(
    embeddings=embeddings,
    collection_name="my_docs",
    connection="postgresql+psycopg://...",
)

pip install -qU langchain-postgres

from langchain_postgres import PGEngine, PGVectorStore

pg_engine = PGEngine.from_connection_string(
    url="postgresql+psycopg://..."
)

vector_store = PGVectorStore.create_sync(
    engine=pg_engine,
    table_name='test_table',
    embedding_service=embedding
)

pip install -qU langchain-pinecone

from langchain_pinecone import PineconeVectorStore
from pinecone import Pinecone

pc = Pinecone(api_key=...)
index = pc.Index(index_name)

vector_store = PineconeVectorStore(embedding=embeddings, index=index)

pip install -qU langchain-qdrant

from qdrant_client.models import Distance, VectorParams
from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient

client = QdrantClient(":memory:")

vector_size = len(embeddings.embed_query("sample text"))

if not client.collection_exists("test"):
    client.create_collection(
        collection_name="test",
        vectors_config=VectorParams(size=vector_size, distance=Distance.COSINE)
    )
vector_store = QdrantVectorStore(
    client=client,
    collection_name="test",
    embedding=embeddings,
)