Azure AI Search 作为 OpenAI 嵌入向量的向量数据库

embeddings_url = "https://cdn.openai.com/API/examples/data/vector_database_wikipedia_articles_embedded.zip"

# The file is ~700 MB so this will take some time
wget.download(embeddings_url)

article_df = pd.read_csv("../../data/vector_database_wikipedia_articles_embedded.csv")

# Read vectors from strings back into a list using json.loads
article_df["title_vector"] = article_df.title_vector.apply(json.loads)
article_df["content_vector"] = article_df.content_vector.apply(json.loads)
article_df["vector_id"] = article_df["vector_id"].apply(str)
article_df.head()

# Initialize the SearchIndexClient
index_client = SearchIndexClient(
    endpoint=search_service_endpoint, credential=credential
)

# Define the fields for the index
fields = [
    SimpleField(name="id", type=SearchFieldDataType.String),
    SimpleField(name="vector_id", type=SearchFieldDataType.String, key=True),
    SimpleField(name="url", type=SearchFieldDataType.String),
    SearchableField(name="title", type=SearchFieldDataType.String),
    SearchableField(name="text", type=SearchFieldDataType.String),
    SearchField(
        name="title_vector",
        type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
        vector_search_dimensions=1536,
        vector_search_profile_name="my-vector-config",
    ),
    SearchField(
        name="content_vector",
        type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
        vector_search_dimensions=1536,
        vector_search_profile_name="my-vector-config",
    ),
]

# Configure the vector search configuration
vector_search = VectorSearch(
    algorithms=[
        HnswAlgorithmConfiguration(
            name="my-hnsw",
            kind=VectorSearchAlgorithmKind.HNSW,
            parameters=HnswParameters(
                m=4,
                ef_construction=400,
                ef_search=500,
                metric=VectorSearchAlgorithmMetric.COSINE,
            ),
        )
    ],
    profiles=[
        VectorSearchProfile(
            name="my-vector-config",
            algorithm_configuration_name="my-hnsw",
        )
    ],
)

# Configure the semantic search configuration
semantic_search = SemanticSearch(
    configurations=[
        SemanticConfiguration(
            name="my-semantic-config",
            prioritized_fields=SemanticPrioritizedFields(
                title_field=SemanticField(field_name="title"),
                keywords_fields=[SemanticField(field_name="url")],
                content_fields=[SemanticField(field_name="text")],
            ),
        )
    ]
)

# Create the search index with the vector search and semantic search configurations
index = SearchIndex(
    name=index_name,
    fields=fields,
    vector_search=vector_search,
    semantic_search=semantic_search,
)

# Create or update the index
result = index_client.create_or_update_index(index)
print(f"{result.name} created")

from azure.core.exceptions import HttpResponseError

# Convert the 'id' and 'vector_id' columns to string so one of them can serve as our key field
article_df["id"] = article_df["id"].astype(str)
article_df["vector_id"] = article_df["vector_id"].astype(str)
# Convert the DataFrame to a list of dictionaries
documents = article_df.to_dict(orient="records")

# Create a SearchIndexingBufferedSender
batch_client = SearchIndexingBufferedSender(
    search_service_endpoint, index_name, credential
)

try:
    # Add upload actions for all documents in a single call
    batch_client.upload_documents(documents=documents)

    # Manually flush to send any remaining documents in the buffer
    batch_client.flush()
except HttpResponseError as e:
    print(f"An error occurred: {e}")
finally:
    # Clean up resources
    batch_client.close()

print(f"Uploaded {len(documents)} documents in total")

# Example function to generate document embedding
def generate_embeddings(text, model):
    # Generate embeddings for the provided text using the specified model
    embeddings_response = client.embeddings.create(model=model, input=text)
    # Extract the embedding data from the response
    embedding = embeddings_response.data[0].embedding
    return embedding


first_document_content = documents[0]["text"]
print(f"Content: {first_document_content[:100]}")

content_vector = generate_embeddings(first_document_content, deployment)
print("Content vector generated")

# Pure Vector Search
query = "modern art in Europe"
  
search_client = SearchClient(search_service_endpoint, index_name, credential)  
vector_query = VectorizedQuery(vector=generate_embeddings(query, deployment), k_nearest_neighbors=3, fields="content_vector")
  
results = search_client.search(  
    search_text=None,  
    vector_queries= [vector_query], 
    select=["title", "text", "url"] 
)
  
for result in results:  
    print(f"Title: {result['title']}")  
    print(f"Score: {result['@search.score']}")  
    print(f"URL: {result['url']}\n")  

# Hybrid Search
query = "Famous battles in Scottish history"  
  
search_client = SearchClient(search_service_endpoint, index_name, credential)  
vector_query = VectorizedQuery(vector=generate_embeddings(query, deployment), k_nearest_neighbors=3, fields="content_vector")
  
results = search_client.search(  
    search_text=query,  
    vector_queries= [vector_query], 
    select=["title", "text", "url"],
    top=3
)
  
for result in results:  
    print(f"Title: {result['title']}")  
    print(f"Score: {result['@search.score']}")  
    print(f"URL: {result['url']}\n")  

# Semantic Hybrid Search
query = "What were the key technological advancements during the Industrial Revolution?"

search_client = SearchClient(search_service_endpoint, index_name, credential)
vector_query = VectorizedQuery(
    vector=generate_embeddings(query, deployment),
    k_nearest_neighbors=3,
    fields="content_vector",
)

results = search_client.search(
    search_text=query,
    vector_queries=[vector_query],
    select=["title", "text", "url"],
    query_type=QueryType.SEMANTIC,
    semantic_configuration_name="my-semantic-config",
    query_caption=QueryCaptionType.EXTRACTIVE,
    query_answer=QueryAnswerType.EXTRACTIVE,
    top=3,
)

semantic_answers = results.get_answers()
for answer in semantic_answers:
    if answer.highlights:
        print(f"Semantic Answer: {answer.highlights}")
    else:
        print(f"Semantic Answer: {answer.text}")
    print(f"Semantic Answer Score: {answer.score}\n")

for result in results:
    print(f"Title: {result['title']}")
    print(f"Reranker Score: {result['@search.reranker_score']}")
    print(f"URL: {result['url']}")
    captions = result["@search.captions"]
    if captions:
        caption = captions[0]
        if caption.highlights:
            print(f"Caption: {caption.highlights}\n")
        else:
            print(f"Caption: {caption.text}\n")