将 Weaviate 与生成式 OpenAI 模块结合使用以进行生成式搜索

# Export OpenAI API Key
!export OPENAI_API_KEY="your key"

# Test that your OpenAI API key is correctly set as an environment variable
# Note. if you run this notebook locally, you will need to reload your terminal and the notebook for the env variables to be live.
import os

# Note. alternatively you can set a temporary env variable like this:
# os.environ["OPENAI_API_KEY"] = 'your-key-goes-here'

if os.getenv("OPENAI_API_KEY") is not None:
    print ("OPENAI_API_KEY is ready")
else:
    print ("OPENAI_API_KEY environment variable not found")

import weaviate
from datasets import load_dataset
import os

# Connect to your Weaviate instance
client = weaviate.Client(
    url="https://your-wcs-instance-name.weaviate.network/",
    # url="https://127.0.0.1:8080/",
    auth_client_secret=weaviate.auth.AuthApiKey(api_key="<YOUR-WEAVIATE-API-KEY>"), # comment out this line if you are not using authentication for your Weaviate instance (i.e. for locally deployed instances)
    additional_headers={
        "X-OpenAI-Api-Key": os.getenv("OPENAI_API_KEY")
    }
)

# Check if your instance is live and ready
# This should return `True`
client.is_ready()

def generative_search_per_item(query, collection_name):
    prompt = "Summarize in a short tweet the following content: {content}"

    result = (
        client.query
        .get(collection_name, ["title", "content", "url"])
        .with_near_text({ "concepts": [query], "distance": 0.7 })
        .with_limit(5)
        .with_generate(single_prompt=prompt)
        .do()
    )
    
    # Check for errors
    if ("errors" in result):
        print ("\033[91mYou probably have run out of OpenAI API calls for the current minute – the limit is set at 60 per minute.")
        raise Exception(result["errors"][0]['message'])
    
    return result["data"]["Get"][collection_name]

query_result = generative_search_per_item("football clubs", "Article")

for i, article in enumerate(query_result):
    print(f"{i+1}. { article['title']}")
    print(article['_additional']['generate']['singleResult']) # print generated response
    print("-----------------------")

def generative_search_group(query, collection_name):
    generateTask = "Explain what these have in common"

    result = (
        client.query
        .get(collection_name, ["title", "content", "url"])
        .with_near_text({ "concepts": [query], "distance": 0.7 })
        .with_generate(grouped_task=generateTask)
        .with_limit(5)
        .do()
    )
    
    # Check for errors
    if ("errors" in result):
        print ("\033[91mYou probably have run out of OpenAI API calls for the current minute – the limit is set at 60 per minute.")
        raise Exception(result["errors"][0]['message'])
    
    return result["data"]["Get"][collection_name]

query_result = generative_search_group("football clubs", "Article")

print (query_result[0]['_additional']['generate']['groupedResult'])