Update app.py

app.py

@@ -1,9 +1,18 @@
 import gradio as gr
+
 from transformers import pipeline
-from langchain_core.prompts import PromptTemplate
-from langchain_core.runnables import RunnableSequence
+
+from langchain import PromptTemplate
+from langchain.document_loaders import WebBaseLoader
+from langchain.schema import StrOutputParser
+from langchain.schema.prompt_template import format_document
+from langchain.chains import LLMChain
 from langchain_google_genai import ChatGoogleGenerativeAI
+
+import ast
 import os
+import getpass
+import matplotlib.pyplot as plt
 
 api_key = os.environ.get('GOOGLE_API_KEY')
 if api_key is None:
@@ -14,6 +23,7 @@ os.environ['GOOGLE_API_KEY'] = api_key
 # Initialize the OCR pipeline
 ocr_pipe = pipeline("image-to-text", model="jinhybr/OCR-Donut-CORD")
 
+
 # Define detailed descriptions
 descriptions = {
     ("Academic", "Task 1"): """You are evaluating an Academic Task 1. The candidate is expected to describe, summarize, or explain a visual representation (such as a graph, chart, table, or diagram). They should write a minimum of 150 words. Key features to look for include:
@@ -109,27 +119,24 @@ Task content: {content}
 '''
 
 # Initialize the LLM
-llm_model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.7, top_p=0.85)
+llm_model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.5, top_p=0.85)
 
 # Define the prompt template
 prompt = PromptTemplate(input_variables=['task_type', 'task_number', 'question', 'content', 'description'], template=initial_prompt)
 
-# Define the RunnableSequence
-sequence = RunnableSequence([
-    prompt,
-    llm_model
-])
+# Define the LLM chain
+chain = LLMChain(
+    llm=llm_model,
+    prompt=prompt,
+)
 
 def evaluate(task_type, task_number, question, image):
     # Process the image to extract text
     text_content = ocr_pipe(image)
     content = text_content[0]['generated_text']
 
-    # Select the appropriate description based on user input
-    description = descriptions.get((task_type, task_number), "")
-
-    # Run the sequence
-    result = sequence({
+    # Run the chain
+    result = chain.run({
         'task_type': task_type,
         'task_number': task_number,
         'question': question,
@@ -147,6 +154,7 @@ inputs = [
     gr.Image(type="pil", label="Upload Image")
 ]
 
+
 outputs = gr.Markdown(label="Result")
 
-gr.Interface(fn=evaluate, inputs=inputs, outputs=outputs, title="IELTS Writing Evaluation").launch(share=True)
+gr.Interface(fn=evaluate, inputs=inputs, outputs=outputs, title="IELTS Writing Evaluation").launch(share=True)