Qdrant 教程：文本相似度搜索

python3 -m venv venvsource venv/bin/activatepip install cohere qdrant-client python-dotenv

[  { "key": "Lion", "desc": "Majestic big cat with golden fur and a loud roar." },  { "key": "Penguin", "desc": "Flightless bird with a tuxedo-like black and white coat." },  { "key": "Gorilla", "desc": "Intelligent primate with muscular build and gentle nature." },  { "key": "Elephant", "desc": "Large mammal with a long trunk and gray skin." },  { "key": "Koala", "desc": "Cute and cuddly marsupial with fluffy ears and a big nose." },  { "key": "Dolphin", "desc": "Playful marine mammal known for its intelligence and acrobatics." },  {    "key": "Orangutan",    "desc": "Shaggy-haired great ape found in the rainforests of Borneo and Sumatra."  },  { "key": "Giraffe", "desc": "Tallest land animal with a long neck and spots on its fur." },  {    "key": "Hippopotamus",    "desc": "Large, semi-aquatic mammal with a wide mouth and stubby legs."  },  { "key": "Kangaroo", "desc": "Marsupial with powerful hind legs and a long tail for balance." },  { "key": "Crocodile", "desc": "Large reptile with sharp teeth and a tough, scaly hide." },  {    "key": "Chimpanzee",    "desc": "Closest relative to humans, known for its intelligence and tool use."  },  { "key": "Tiger", "desc": "Striped big cat with incredible speed and agility." },  { "key": "Zebra", "desc": "Striped mammal with a distinctive mane and tail." },  { "key": "Ostrich", "desc": "Flightless bird with long legs and a big, fluffy tail." },  { "key": "Rhino", "desc": "Large, thick-skinned mammal with a horn on its nose." },  { "key": "Cheetah", "desc": "Fastest land animal with a spotted coat and sleek build." },  {    "key": "Polar Bear",    "desc": "Arctic bear with a thick white coat and webbed paws for swimming."  },  { "key": "Peacock", "desc": "Colorful bird with a vibrant tail of feathers." },  { "key": "Kangaroo", "desc": "Marsupial with powerful hind legs and a long tail for balance." },  {    "key": "Octopus",    "desc": "Intelligent sea creature with eight tentacles and the ability to change color."  },  { "key": "Whale", "desc": "Enormous marine mammal with a blowhole on top of its head." },  { "key": "Sloth", "desc": "Slow-moving mammal found in the rainforests of South America." },  { "key": "Flamingo", "desc": "Tall, pink bird with long legs and a curved beak." }]

QDRANT_API_KEY=<qdrant-api-keu>QDRANT_HOST=<qdrant-host>COHERE_API_KEY=<cohere-api-key>

import jsonimport osimport uuidfrom typing import Dict, Listimport coherefrom dotenv import load_dotenvfrom qdrant_client import QdrantClientfrom qdrant_client.http import models

load_dotenv()QDRANT_API_KEY = os.getenv("QDRANT_API_KEY")QDRANT_HOST = os.getenv("QDRANT_HOST")COHERE_API_KEY = os.getenv("COHERE_API_KEY")COHERE_SIZE_VECTOR = 4096  # Larger modelif not QDRANT_API_KEY:    raise ValueError("QDRANT_API_KEY is not set")if not QDRANT_HOST:    raise ValueError("QDRANT_HOST is not set")if not COHERE_API_KEY:    raise ValueError("COHERE_API_KEY is not set")

class SearchClient:    def __init__(        self,        qdrabt_api_key: str = QDRANT_API_KEY,        qdrant_host: str = QDRANT_HOST,        cohere_api_key: str = COHERE_API_KEY,        collection_name: str = "animal",    ):        self.qdrant_client = QdrantClient(host=qdrant_host, api_key=qdrabt_api_key)        self.collection_name = collection_name        self.qdrant_client.recreate_collection(            collection_name=self.collection_name,            vectors_config=models.VectorParams(                size=COHERE_SIZE_VECTOR, distance=models.Distance.COSINE            ),        )        self.co_client = cohere.Client(api_key=cohere_api_key)    # Qdrant requires data in float format    def _float_vector(self, vector: List[float]):        return list(map(float, vector))    # Embedding using Cohere Embed model    def _embed(self, text: str):        return self.co_client.embed(texts=[text]).embeddings[0]    # Prepare Qdrant Points    def _qdrant_format(self, data: List[Dict[str, str]]):        points = [            models.PointStruct(                id=uuid.uuid4().hex,                payload={"key": point["key"], "desc": point["desc"]},                vector=self._float_vector(self._embed(point["desc"])),            )            for point in data        ]        return points    # Index data    def index(self, data: List[Dict[str, str]]):        """        data: list of dict with keys: "key" and "desc"        """        points = self._qdrant_format(data)        result = self.qdrant_client.upsert(            collection_name=self.collection_name, points=points        )        return result    # Search using text query    def search(self, query_text: str, limit: int = 3):        query_vector = self._embed(query_text)        return self.qdrant_client.search(            collection_name=self.collection_name,            query_vector=self._float_vector(query_vector),            limit=limit,        )

if __name__ == "__main__":    client = SearchClient()    # import data from data.json file    with open("data.json", "r") as f:        data = json.load(f)    index_result = client.index(data)    print(index_result)    print("====")    search_result = client.search(        "Tallest animal in the world, quite long neck.",    )    print(search_result)

operation_id=0 status=<UpdateStatus.COMPLETED: 'completed'>===[ScoredPoint(id='d17eb61c-8764-4bdb-bb26-ac66c3ffa220', version=0, score=0.8677041, payload={'desc': 'Tallest land animal with a long neck and spots on its fur.', 'key': 'Giraffe'}, vector=None), ScoredPoint(id='4934a842-8c55-42bc-938f-a839be2505de', version=0, score=0.71296465, payload={'desc': 'Large, semi-aquatic mammal with a wide mouth and stubby legs.', 'key': 'Hippopotamus'}, vector=None), ScoredPoint(id='05d7e73c-a8bf-44f9-a8b4-af82e06719d0', version=0, score=0.69240415, payload={'desc': 'Large, thick-skinned mammal with a horn on its nose.', 'key': 'Rhino'}, vector=None)]