weaviate_quickstart_collection_creation_and_near_text_search.py

1import weaviate
2import weaviate.classes.config as wc
3import os
4import requests
5import json
6
7# Best practice: store your credentials in environment variables
8# WEAVIATE_URL = os.getenv("WEAVIATE_URL")
9# WEAVIATE_API_KEY = os.getenv("WEAVIATE_API_KEY")
10# COHERE_API_KEY = os.getenv("COHERE_API_KEY")
11
12client = weaviate.connect_to_weaviate_cloud(
13    cluster_url="https://your-weaviate-endpoint.weaviate.network",  # Replace with your URL
14    auth_credentials=weaviate.auth.AuthApiKey("your-weaviate-api-key"),  # Replace with your API key
15    headers={
16        "X-Cohere-Api-Key": "your-cohere-api-key"  # Replace with your inference API key
17    }
18)
19
20try:
21    # 1. Create a collection
22    questions = client.collections.create(
23        name="Question",
24        vectorizer_config=wc.Configure.Vectorizer.text2vec_cohere(),  # Configure the Cohere vectorizer
25        generative_config=wc.Configure.Generative.cohere()            # Configure the Cohere generative module
26    )
27
28    # 2. Load data
29    resp = requests.get('https://raw.githubusercontent.com/weaviate-tutorials/quickstart/main/data/jeopardy_tiny.json')
30    data = resp.json()
31
32    # 3. Insert objects
33    with questions.get_bulk_writer() as batch:
34        for i, d in enumerate(data):
35            batch.add_object({
36                "answer": d["Answer"],
37                "question": d["Question"],
38                "category": d["Category"],
39            })
40
41    # 4. Perform a search
42    response = questions.query.near_text(
43        query="biology",
44        limit=2
45    )
46
47    for obj in response.objects:
48        print(f"ID: {obj.uuid}")
49        print(f"Data: {json.dumps(obj.properties, indent=2)}")
50
51finally:
52    client.close()