Update app.py

app.py

@@ -6,34 +6,46 @@ from transformers import pipeline
 from sklearn.metrics.pairwise import cosine_similarity
 from docx import Document
 import io
+import re
 
 class CarbonCreditDocGenerator:
     def __init__(self):
         self.sbert_model = SentenceTransformer('all-MiniLM-L6-v2')
-        self.nlg_pipeline = pipeline("text-generation", model="gpt2", max_length=500)
-        
-        # Load your knowledge base here
+        self.nlg_pipeline = pipeline("text-generation", model="gpt2", max_length=1000)
         self.knowledge_base = self.load_knowledge_base()
         
     def load_knowledge_base(self):
-        # This should load your carbon credit domain knowledge
         return [
             "Carbon credits represent the reduction of one metric ton of carbon dioxide emissions.",
             "Afforestation projects involve planting trees in areas where there were none before.",
             "The Verified Carbon Standard (VCS) is a widely recognized certification for carbon credits.",
             "Carbon credit projects must demonstrate additionality, meaning the reductions wouldn't have occurred without the project.",
             "Monitoring, reporting, and verification (MRV) are crucial components of carbon credit projects.",
-            # Add more knowledge base entries...
+            "Project developers must provide detailed information about project location, type, and expected carbon sequestration.",
+            "Carbon credit pricing can vary based on project type, location, and additional benefits.",
+            "Environmental Impact Assessments (EIA) are often required for carbon credit projects.",
+            "Community engagement and social benefits are important aspects of many carbon credit projects.",
+            "Risk assessment and mitigation strategies are crucial for project success and credibility."
         ]
         
     def process_input_data(self, input_text):
-        # In a real scenario, you'd parse the input document more thoroughly
-        lines = input_text.split('\n')
+        sections = re.split(r'\d+\.\s+', input_text)[1:]  # Split by numbered sections
         data = {}
-        for line in lines:
-            if ':' in line:
-                key, value = line.split(':', 1)
-                data[key.strip()] = value.strip()
+        current_section = ""
+        for section in sections:
+            lines = section.strip().split('\n')
+            section_title = lines[0].strip()
+            current_section = section_title
+            data[current_section] = {}
+            for line in lines[1:]:
+                if ':' in line:
+                    key, value = line.split(':', 1)
+                    data[current_section][key.strip()] = value.strip()
+                else:
+                    # Append to the last key if no colon is found
+                    if data[current_section]:
+                        last_key = list(data[current_section].keys())[-1]
+                        data[current_section][last_key] += " " + line.strip()
         return data
     
     def retrieve_relevant_knowledge(self, query, top_k=3):
@@ -45,30 +57,31 @@ class CarbonCreditDocGenerator:
         
         return [self.knowledge_base[i] for i in top_indices]
     
-    def generate_section_content(self, section_title, input_data, max_length=500):
+    def generate_section_content(self, section_title, input_data, max_length=1000):
         query = f"Generate content for the '{section_title}' section of a carbon credit document."
         relevant_knowledge = self.retrieve_relevant_knowledge(query)
         
-        context = f"Input data: {input_data}\n\nRelevant knowledge: {' '.join(relevant_knowledge)}"
+        section_data = input_data.get(section_title, input_data)
+        context = f"Input data: {section_data}\n\nRelevant knowledge: {' '.join(relevant_knowledge)}"
         prompt = f"{context}\n\nTask: {query}\n\nContent:"
         
         generated_text = self.nlg_pipeline(prompt, max_length=max_length, num_return_sequences=1)[0]['generated_text']
         
-        # Apply corrective RAG
-        corrected_text = self.apply_corrective_rag(generated_text, input_data, relevant_knowledge)
+        corrected_text = self.apply_corrective_rag(generated_text, section_data, relevant_knowledge)
         
         return corrected_text
     
     def apply_corrective_rag(self, generated_text, input_data, relevant_knowledge):
-        # This is a simplified version of corrective RAG
         corrected_text = generated_text
         
-        # Ensure all input data is represented
         for key, value in input_data.items():
-            if value.lower() not in corrected_text.lower():
+            if isinstance(value, dict):
+                for sub_key, sub_value in value.items():
+                    if sub_value.lower() not in corrected_text.lower():
+                        corrected_text += f" {sub_key}: {sub_value}."
+            elif value.lower() not in corrected_text.lower():
                 corrected_text += f" {key}: {value}."
         
-        # Ensure relevant knowledge is incorporated
         for knowledge in relevant_knowledge:
             if knowledge.lower() not in corrected_text.lower():
                 corrected_text += f" {knowledge}"
@@ -82,17 +95,14 @@ class CarbonCreditDocGenerator:
         input_data = self.process_input_data(input_text)
         
         sections = [
-            "Executive Summary",
-            "Certificate Identification",
-            "Emission Reduction Details",
-            "Project Information",
-            "Verification and Certification",
-            "Issuance and Expiration Dates",
-            "Market Type",
-            "Transferability Information",
-            "Legal Framework",
-            "Accountability Measures",
-            "Contact Information"
+            "Project Overview",
+            "Seller/Proponent Information",
+            "Carbon Credit Specifications",
+            "Financial & Pricing Information",
+            "Project Impact and Sustainability",
+            "Risks & Mitigation Strategies",
+            "Supporting Documentation",
+            "Declarations and Acknowledgements"
         ]
         
         for section in sections:
@@ -104,41 +114,57 @@ class CarbonCreditDocGenerator:
     
     def generate_document(self, input_text):
         doc = self.create_document(input_text)
-        
-        # Save the document to a BytesIO object
         doc_io = io.BytesIO()
         doc.save(doc_io)
         doc_io.seek(0)
-        
         return doc_io
 
 # Streamlit app
 def main():
+    st.set_page_config(page_title="Carbon Credit Document Generator", page_icon="🌿")
     st.title("Carbon Credit Document Generator")
 
-    # File uploader
-    uploaded_file = st.file_uploader("Choose a text file", type="txt")
+    st.markdown("""
+    This app generates a comprehensive Carbon Credit Project Document based on your input.
+    Upload a text file or paste your project details below.
+    """)
+
+    input_method = st.radio("Choose input method:", ("Upload File", "Paste Text"))
+
+    if input_method == "Upload File":
+        uploaded_file = st.file_uploader("Choose a text file", type="txt")
+        if uploaded_file is not None:
+            input_text = uploaded_file.read().decode("utf-8")
+            st.text_area("File Contents (Read-only)", input_text, height=300, disabled=True)
+    else:
+        input_text = st.text_area("Paste your project details here:", height=400, help="Enter your project details in a structured format, similar to the Carbon Credit Project Submission Form.")
 
-    if uploaded_file is not None:
-        # Read the file
-        input_text = uploaded_file.read().decode("utf-8")
-        st.text_area("Input Data", input_text, height=200)
+    if st.button("Generate Document"):
+        if not input_text:
+            st.error("Please provide input data before generating the document.")
+        else:
+            try:
+                generator = CarbonCreditDocGenerator()
+                
+                with st.spinner("Generating document... This may take a few moments."):
+                    doc_io = generator.generate_document(input_text)
 
-        if st.button("Generate Document"):
-            generator = CarbonCreditDocGenerator()
-            
-            with st.spinner("Generating document..."):
-                doc_io = generator.generate_document(input_text)
+                st.success("Document generated successfully!")
 
-            st.success("Document generated successfully!")
+                st.download_button(
+                    label="📥 Download Carbon Credit Document",
+                    data=doc_io.getvalue(),
+                    file_name="carbon_credit_document.docx",
+                    mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+                )
+                
+                st.info("Your document is ready for download. Click the button above to save it.")
+            except Exception as e:
+                st.error(f"An error occurred while generating the document: {str(e)}")
+                st.info("Please try again or contact support if the problem persists.")
 
-            # Provide download button
-            st.download_button(
-                label="Download Carbon Credit Document",
-                data=doc_io.getvalue(),
-                file_name="carbon_credit_document.docx",
-                mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
-            )
+    st.markdown("---")
+    st.markdown("Developed with ❤️ by Your Company Name")
 
 if __name__ == "__main__":
     main()