兼容Azure OpenAI

CosmosShadow · Jul 2, 2024 · 68826e5 · 68826e5
1 parent e1fb8f0
commit 68826e5
Show file tree

Hide file tree

Showing 3 changed files with 28 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -66,7 +66,10 @@ parse pdf file to markdown file, and return markdown content and all image paths
 
 - **base_url**: OpenAI Base URL. (optional). If not provided, Use OPENAI_BASE_URL environment variable.
 
-- **model**: OpenAI Vision Large Model, default is 'gpt-4o'. You also can use [qwen-vl-max](https://help.aliyun.com/zh/dashscope/developer-reference/vl-plus-quick-start), [GLM-4V](https://open.bigmodel.cn/dev/api#glm-4v) by change the `OPENAI_BASE_URL` or specify `base_url`.
+- **model**: OpenAI Vision Large Model, default is 'gpt-4o'. 
+        You also can use [qwen-vl-max](https://help.aliyun.com/zh/dashscope/developer-reference/vl-plus-quick-start) (not tested yet)
+        [GLM-4V](https://open.bigmodel.cn/dev/api#glm-4v) by change the `OPENAI_BASE_URL` or specify `base_url`. 
+        Also you can use Azure OpenAI by specify `base_url` to `https://xxxx.openai.azure.com/`, api_key is Azure API Key, model is like 'azure_xxxx' where xxxx is the deployed model name (not openai model name)
 
 - **verbose**: verbose mode
 

diff --git a/README_CN.md b/README_CN.md
@@ -66,7 +66,12 @@ print(content)
 
 - **base_url**：OpenAI 基本 URL。（可选）。如果未提供，则使用 OPENAI_BASE_URL 环境变量。
 
-- **model**：OpenAI API格式的多模态大模型，默认为 “gpt-4o”。如果您需要使用其他模型，例如 [qwen-vl-max](https://help.aliyun.com/zh/dashscope/developer-reference/vl-plus-quick-start), [GLM-4V](https://open.bigmodel.cn/dev/api#glm-4v), 可以通过修改环境变量 `OPENAI_BASE_URL` 或 指定API参数 `base_url` 来使用。
+- **model**：OpenAI API格式的多模态大模型，默认为 “gpt-4o”。
+    如果您需要使用其他模型，例如 [qwen-vl-max](https://help.aliyun.com/zh/dashscope/developer-reference/vl-plus-quick-start) (尚未测试)
+
+    [GLM-4V](https://open.bigmodel.cn/dev/api#glm-4v), 可以通过修改环境变量 `OPENAI_BASE_URL` 或 指定API参数 `base_url` 来使用。 (已经测试)
+
+    您也可以通过将 `base_url` 指定为 `https://xxxx.openai.azure.com/` 来使用 Azure OpenAI，api_key 是 Azure API 密钥，模型类似于 'azure_xxxx'，其中 xxxx 是部署的模型名称（不是 openai 模型名称）(已经测试)
 
 - **verbose**：详细模式
 

diff --git a/test/test.py b/test/test.py
@@ -27,7 +27,23 @@ def test_use_env():
     print(image_paths)
     # also output_dir/output.md is generated
 
+def test_azure():
+    from gptpdf import parse_pdf
+    api_key = '8ef0b4df45e444079cd5a4xxxxx' # Azure API Key
+    base_url = 'https://xxx.openai.azure.com/' # Azure API Base URL
+    model = 'azure_xxxx' # azure_ with deploy ID name (not open ai model name), e.g. azure_cpgpt4
+
+    pdf_path = '../examples/attention_is_all_you_need.pdf'
+    output_dir = '../examples/attention_is_all_you_need/'
+    # Use OPENAI_API_KEY and OPENAI_API_BASE from environment variables
+    content, image_paths = parse_pdf(pdf_path, output_dir=output_dir, api_key=api_key, base_url=base_url, model=model, verbose=True)
+    print(content)
+    print(image_paths)
+
+
+
 
 if __name__ == '__main__':
-    test_use_api_key()
-    # test_use_env()
+    # test_use_api_key()
+    # test_use_env()
+    test_azure()