Add application file

app.py

@@ -1,23 +1,26 @@
-import gradio as gr
-import os
-from PIL import Image
-from langchain.tools import BaseTool
-import torch
-from transformers import BlipProcessor, BlipForConditionalGeneration
 from langchain.agents import load_tools
 from langchain.agents import initialize_agent
-from langchain.chat_models import ChatOpenAI
+from langchain.agents import AgentType
+from langchain.llms import OpenAI
+# from langchain.chat_models import ChatOpenAI
 from langchain.chat_models import AzureChatOpenAI
-from langchain.prompts import PromptTemplate
-from langchain.chains import LLMChain
 from langchain.chains.conversation.memory import ConversationBufferWindowMemory
+import os
+from langchain.tools import BaseTool
+import torch
 from transformers import BlipProcessor, BlipForConditionalGeneration
+from transformers.models.oneformer.modeling_oneformer import OneFormerModelOutput
+import requests
+from PIL import Image
+import gradio as gr
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
 
-
-OPENAI_API_KEY=os.getenv("OPENAI_API_KEY")
-OPENAI_API_BASE=os.getenv("OPENAI_API_BASE")
-DEPL_NAME=os.getenv("deployment_name")
-llm=AzureChatOpenAI(deployment_name=DEPL_NAME,openai_api_base=OPENAI_API_BASE,openai_api_key=OPENAI_API_KEY,openai_api_version="2023-03-15-preview",model_name="gpt-3.5-turbo")
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+OPENAI_API_BASE = os.getenv("OPENAI_API_BASE")
+DEP_NAME = os.getenv("deployment_name")
+llm = AzureChatOpenAI(deployment_name=DEP_NAME, openai_api_base=OPENAI_API_BASE, openai_api_key=OPENAI_API_KEY,
+                      openai_api_version="2023-03-15-preview", model_name="gpt-3.5-turbo")
 
 image_to_text_model = "Salesforce/blip-image-captioning-large"
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
@@ -27,6 +30,7 @@ processor = BlipProcessor.from_pretrained(image_to_text_model)
 
 
 def describeImage(image_url):
+    # image_object = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
     image_object = Image.open(image_url).convert('RGB')
     # image
     inputs = processor(image_object, return_tensors="pt").to(device)
@@ -97,4 +101,4 @@ with gr.Blocks() as demo:
     submit_btn = gr.Button('提交', variant="primary")
     submit_btn.click(image_to_txt, inputs=[image_url, user_input], outputs=output)
 
-demo.launch()
+demo.launch()