使用 LangChain 实现语义搜索

pip install langchain openai meilisearch python-dotenv

# .env

MEILI_HTTP_ADDR="your Meilisearch host"
MEILI_API_KEY="your Meilisearch API key"
OPENAI_API_KEY="your OpenAI API key"

# setup.py

import os
from dotenv import load_dotenv # remove if not using dotenv
from langchain.vectorstores import Meilisearch
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.document_loaders import JSONLoader

load_dotenv() # remove if not using dotenv

# exit if missing env vars
if "MEILI_HTTP_ADDR" not in os.environ:
    raise Exception("Missing MEILI_HTTP_ADDR env var")
if "MEILI_API_KEY" not in os.environ:
    raise Exception("Missing MEILI_API_KEY env var")
if "OPENAI_API_KEY" not in os.environ:
    raise Exception("Missing OPENAI_API_KEY env var")

# Setup code will go here 👇

# setup.py

# previous code

# Load documents
loader = JSONLoader(
    file_path="./movies-lite.json",
    jq_schema=".[] | {id: .id, overview: .overview, title: .title}",
    text_content=False,
)
documents = loader.load()
print("Loaded {} documents".format(len(documents)))

# Store documents in Meilisearch
embeddings = OpenAIEmbeddings()
embedders = { 
        "custom": {
            "source": "userProvided",
            "dimensions": 1536
        }
    }
embedder_name = "custom" 
vector_store = Meilisearch.from_documents(documents=documents, embedding=embeddings, embedders=embedders, embedder_name=embedder_name)

print("Started importing documents")

# search.py

import os
from dotenv import load_dotenv
from langchain.vectorstores import Meilisearch
from langchain.embeddings.openai import OpenAIEmbeddings
import meilisearch

load_dotenv()

# You can use the same code as `setup.py` to check for missing env vars

# Create the vector store
client = meilisearch.Client(
    url=os.environ.get("MEILI_HTTP_ADDR"),
    api_key=os.environ.get("MEILI_API_KEY"),
)
embeddings = OpenAIEmbeddings()
vector_store = Meilisearch(client=client, embedding=embeddings)

# Make similarity search
embedder_name = "custom"
query = "superhero fighting evil in a city at night"
results = vector_store.similarity_search(
    query=query,
    embedder_name=embedder_name,
    k=3,
)

# Display results
for result in results:
    print(result.page_content)

{"id": 155, "title": "The Dark Knight", "overview": "Batman raises the stakes in his war on crime. With the help of Lt. Jim Gordon and District Attorney Harvey Dent, Batman sets out to dismantle the remaining criminal organizations that plague the streets. The partnership proves to be effective, but they soon find themselves prey to a reign of chaos unleashed by a rising criminal mastermind known to the terrified citizens of Gotham as the Joker."}
{"id": 314, "title": "Catwoman", "overview": "Liquidated after discovering a corporate conspiracy, mild-mannered graphic artist Patience Phillips washes up on an island, where she's resurrected and endowed with the prowess of a cat -- and she's eager to use her new skills ... as a vigilante. Before you can say \"cat and mouse,\" handsome gumshoe Tom Lone is on her tail."}
{"id": 268, "title": "Batman", "overview": "Batman must face his most ruthless nemesis when a deformed madman calling himself \"The Joker\" seizes control of Gotham's criminal underworld."}