Programmiererforum

from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import (
SimpleField,
SearchFieldDataType,
SearchableField,
SearchField,
VectorSearch,
HnswAlgorithmConfiguration,
VectorSearchProfile,
SemanticConfiguration,
SemanticPrioritizedFields,
SemanticField,
SemanticSearch,
SearchIndex,
AzureOpenAIVectorizer,
AzureOpenAIVectorizerParameters
)

# Azure Cognitive Search setup
service_endpoint = "https://yourserviceendpoint.search.windows.net"
admin_key = "ABC"
index_name = "courses-index"

# Wrap admin_key in AzureKeyCredential
credential = AzureKeyCredential(admin_key)

# Create the index client with AzureKeyCredential
index_client = SearchIndexClient(endpoint=service_endpoint, credential=credential)

# Define the index schema
fields = [
SimpleField(name="id", type="Edm.String", key=True),
SimpleField(name="content", type="Edm.String"),
SearchField(
name="embedding",
type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
searchable=True,
vector_search_dimensions=384,
vector_search_profile_name="myHnswProfile"
)
# SearchField(name="embedding", type='Collection(Edm.Single)', searchable=True)
]

# Configure the vector search configuration
vector_search = VectorSearch(
algorithms=[
HnswAlgorithmConfiguration(
name="myHnsw"
)
],
profiles=[
VectorSearchProfile(
name="myHnswProfile",
algorithm_configuration_name="myHnsw"
)
]
)

# Create the index
index = SearchIndex(
name=index_name,
fields=fields,
vector_search=vector_search
)

# Send the index creation request
index_client.create_index(index)

print(f"Index '{index_name}' created successfully.")

from azure.search.documents import SearchClient

# Generate embeddings and upload data
search_client = SearchClient(endpoint=service_endpoint, index_name=index_name, credential=credential)

documents = []
for i, row in courses_pd.iterrows():
document = {
"id": str(i),
"content": row["content"],
"embedding": row["embeddings"]  # Ensure embeddings are a list of floats
}
documents.append(document)

# Upload documents to the index
search_client.upload_documents(documents=documents)
print(f"Uploaded {len(documents)} documents to Azure Cognitive Search.")

from azure.search.documents.models import VectorQuery

# Generate embedding for the query
query = "machine learning"
query_embedding = model.encode(query).tolist()  # Convert to list of floats

# Create a VectorQuery
vector_query = VectorQuery(
vector=query_embedding,
k=3,  # Number of nearest neighbors
fields="embedding"  # Name of the field where embeddings are stored
)

# Perform the search
results = search_client.search(
vector_queries=[vector_query],
select=["id", "content"]
)

# Print the results
for result in results:
print(f"ID: {result['id']}, Content: {result['content']}")

vector is not a known attribute of class  and will be ignored
k is not a known attribute of class  and will be ignored
HttpResponseError: (InvalidRequestParameter) The vector query's 'kind' parameter is not set.

Ich wollte eine Azure Cognitive Search erstellen, um den Kurskatalog mithilfe von Vektoren abzufragen. Ich habe einen Pandas-Datenrahmen mit dem Namen „courses_pd“ und er hat zwei Spalten, „Inhalt“ und „Einbettungen“. Dies ist die Einbettung, die ich mit model = SentenceTransformer('all-MiniLM-L6-v2') und dann model.encode(x) erstellt habe.
Unten finden Sie den Python-Codeausschnitt, der den Index in ACS erstellt und die Dokumente aus dem Azure Databricks-Notebook hochlädt.
[code]from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import (
SimpleField,
SearchFieldDataType,
SearchableField,
SearchField,
VectorSearch,
HnswAlgorithmConfiguration,
VectorSearchProfile,
SemanticConfiguration,
SemanticPrioritizedFields,
SemanticField,
SemanticSearch,
SearchIndex,
AzureOpenAIVectorizer,
AzureOpenAIVectorizerParameters
)

# Azure Cognitive Search setup
service_endpoint = "https://yourserviceendpoint.search.windows.net"
admin_key = "ABC"
index_name = "courses-index"

# Wrap admin_key in AzureKeyCredential
credential = AzureKeyCredential(admin_key)

# Create the index client with AzureKeyCredential
index_client = SearchIndexClient(endpoint=service_endpoint, credential=credential)

# Define the index schema
fields = [
SimpleField(name="id", type="Edm.String", key=True),
SimpleField(name="content", type="Edm.String"),
SearchField(
name="embedding",
type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
searchable=True,
vector_search_dimensions=384,
vector_search_profile_name="myHnswProfile"
)
# SearchField(name="embedding", type='Collection(Edm.Single)', searchable=True)
]

# Configure the vector search configuration
vector_search = VectorSearch(
algorithms=[
HnswAlgorithmConfiguration(
name="myHnsw"
)
],
profiles=[
VectorSearchProfile(
name="myHnswProfile",
algorithm_configuration_name="myHnsw"
)
]
)

# Create the index
index = SearchIndex(
name=index_name,
fields=fields,
vector_search=vector_search
)

# Send the index creation request
index_client.create_index(index)

print(f"Index '{index_name}' created successfully.")
[/code]
Und dann laden Sie das Dokument mit dem folgenden Code hoch:
[code]from azure.search.documents import SearchClient

# Generate embeddings and upload data
search_client = SearchClient(endpoint=service_endpoint, index_name=index_name, credential=credential)

documents = []
for i, row in courses_pd.iterrows():
document = {
"id": str(i),
"content": row["content"],
"embedding": row["embeddings"] # Ensure embeddings are a list of floats
}
documents.append(document)

# Upload documents to the index
search_client.upload_documents(documents=documents)
print(f"Uploaded {len(documents)} documents to Azure Cognitive Search.")
[/code]
Wenn ich jetzt den search_client abfrage, erhalte ich mehrere Fehler. Wenn ich mit einer Rohzeichenfolge suche oder nachdem ich model.encode(str) ausgeführt habe, wird ein , aber die Suche schlägt im Protokoll fehl.
[code]from azure.search.documents.models import VectorQuery

# Generate embedding for the query
query = "machine learning"
query_embedding = model.encode(query).tolist() # Convert to list of floats

# Create a VectorQuery
vector_query = VectorQuery(
vector=query_embedding,
k=3, # Number of nearest neighbors
fields="embedding" # Name of the field where embeddings are stored
)

# Perform the search
results = search_client.search(
vector_queries=[vector_query],
select=["id", "content"]
)

# Print the results
for result in results:
print(f"ID: {result['id']}, Content: {result['content']}")
[/code]
Der Fehler lautet dann:
[code]vector is not a known attribute of class and will be ignored
k is not a known attribute of class and will be ignored
HttpResponseError: (InvalidRequestParameter) The vector query's 'kind' parameter is not set.
[/code]
Dann habe ich versucht, kind = 'vector' als Parameter in VectorQuery anzugeben, dann heißt es, dass kind nicht festgelegt ist!
Dokumente werden hochgeladen und der Index wird erstellt, wie ich im Portal sehen kann.
[img]https://i.sstatic.net/wizBjLoY.png[/img]

Ich muss etwas tun Falsch, entweder die Art und Weise, wie ich den Suchindex eingerichtet habe oder die Art und Weise, wie ich den Index abfrage, die Dokumentation und die Github-Codebasis bieten diesbezüglich nichts, daher ist die Suche nach Hilfe in der Community neu in diesem Bereich.