Azure OpenAI¶

遗憾的是，Azure OpenAI 资源与标准 OpenAI 资源存在差异，除非使用嵌入模型，否则无法生成嵌入向量。这些模型可用的区域可在此处查阅：https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/models#embeddings-models

更遗憾的是，支持嵌入模型的区域并不支持最新版本（<*>-003）的 OpenAI 模型，因此我们不得不使用一个区域处理嵌入，而用另一个区域处理文本生成。

如果您在 Colab 上打开此 Notebook，可能需要安装 LlamaIndex 🦙。

In [ ]:

Copied!

%pip install llama-index-embeddings-azure-openai
%pip install llama-index-llms-azure-openai
%pip install llama-index-embeddings-azure-openai
%pip install llama-index-llms-azure-openai

In [ ]:

Copied!

!pip install llama-index
!pip install llama-index

In [ ]:

Copied!





from llama_index.llms.azure_openai import AzureOpenAI
from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
import logging
import sys

logging.basicConfig(
    stream=sys.stdout, level=logging.INFO
)  # logging.DEBUG for more verbose output
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
from llama_index.llms.azure_openai import AzureOpenAI
from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
import logging
import sys

logging.basicConfig(
    stream=sys.stdout, level=logging.INFO
)  # logging.DEBUG for more verbose output
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

在此，我们配置嵌入模型（用于检索）和大语言模型（用于文本生成）。
请注意，您不仅需要模型名称（例如 "text-embedding-ada-002"），还需要模型部署名称（即在 Azure 中部署模型时您选择的名称）。
初始化 AzureOpenAI 和 OpenAIEmbedding 时，必须将部署名称作为参数传入。

In [ ]:

Copied!





api_key = "<api-key>"
azure_endpoint = "https://<your-resource-name>.openai.azure.com/"
api_version = "2023-07-01-preview"

llm = AzureOpenAI(
    model="gpt-35-turbo-16k",
    deployment_name="my-custom-llm",
    api_key=api_key,
    azure_endpoint=azure_endpoint,
    api_version=api_version,
)

# You need to deploy your own embedding model as well as your own chat completion model
embed_model = AzureOpenAIEmbedding(
    model="text-embedding-ada-002",
    deployment_name="my-custom-embedding",
    api_key=api_key,
    azure_endpoint=azure_endpoint,
    api_version=api_version,
)
api_key = ""
azure_endpoint = "https://.openai.azure.com/"
api_version = "2023-07-01-preview"

llm = AzureOpenAI(
    model="gpt-35-turbo-16k",
    deployment_name="my-custom-llm",
    api_key=api_key,
    azure_endpoint=azure_endpoint,
    api_version=api_version,
)

# You need to deploy your own embedding model as well as your own chat completion model
embed_model = AzureOpenAIEmbedding(
    model="text-embedding-ada-002",
    deployment_name="my-custom-embedding",
    api_key=api_key,
    azure_endpoint=azure_endpoint,
    api_version=api_version,
)

In [ ]:

Copied!

from llama_index.core import Settings

Settings.llm = llm
Settings.embed_model = embed_model
from llama_index.core import Settings

Settings.llm = llm
Settings.embed_model = embed_model

In [ ]:

Copied!





documents = SimpleDirectoryReader(
    input_files=["../../data/paul_graham/paul_graham_essay.txt"]
).load_data()
index = VectorStoreIndex.from_documents(documents)
documents = SimpleDirectoryReader(
    input_files=["../../data/paul_graham/paul_graham_essay.txt"]
).load_data()
index = VectorStoreIndex.from_documents(documents)

INFO:httpx:HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"

In [ ]:

Copied!





query = "What is most interesting about this essay?"
query_engine = index.as_query_engine()
answer = query_engine.query(query)

print(answer.get_formatted_sources())
print("query was:", query)
print("answer was:", answer)
query = "What is most interesting about this essay?"
query_engine = index.as_query_engine()
answer = query_engine.query(query)

print(answer.get_formatted_sources())
print("query was:", query)
print("answer was:", answer)

INFO:httpx:HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-embedding/embeddings?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-llm/chat/completions?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-llm/chat/completions?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
HTTP Request: POST https://test-simon.openai.azure.com//openai/deployments/my-custom-llm/chat/completions?api-version=2023-07-01-preview "HTTP/1.1 200 OK"
> Source (Doc id: 3e0d1e3f-9099-483f-9abd-8f352c5e730f): A lot of Lisp hackers dream of building a new Lisp, partly because one of the distinctive feature...

> Source (Doc id: 06c1d986-1856-44cd-980d-651252ad1caf): What I Worked On

February 2021

Before college the two main things I worked on, outside of schoo...
query was: What is most interesting about this essay?
answer was: The most interesting aspect of this essay is the author's exploration of the transformative power of publishing essays online. The author reflects on how the internet has democratized the publishing process, allowing anyone to publish their work and reach a wide audience. This realization led the author to start writing and publishing essays online, which eventually became a significant part of their work. The author also discusses the initial skepticism and lack of prestige associated with online essays, but they find encouragement in the potential for genuine discovery and the absence of the desire to impress others. Overall, the essay highlights the author's personal journey and the impact of online publishing on their career.