Enhance .gitignore to include additional Python, environment, IDE, and model file exclusions. Refactor app.py to improve text generation pipeline initialization with better error handling and enhanced prompt structure for email generation. Update requirements.txt to specify minimum versions for dependencies, ensuring compatibility and stability.

.gitignore

@@ -1,2 +1,43 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Environment variables
 .env
-.venv
+
+# Virtual Environment
+venv/
+ENV/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Streamlit
+.streamlit/
+
+# Model files
+*.pt
+*.pth
+*.bin

app.py

@@ -60,22 +60,35 @@ if st.session_state.parsed_cv:
 if access_token:
     @st.cache_resource
     def initialize_pipeline(access_token):
-        tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", token=access_token)
-        model = AutoModelForCausalLM.from_pretrained(
-            "google/gemma-2b-it",
-            torch_dtype="bfloat16",
-            token=access_token
-        )
-        return pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512)
+        try:
+            tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", token=access_token)
+            model = AutoModelForCausalLM.from_pretrained(
+                "google/gemma-2b-it",
+                token=access_token,
+                device_map="auto"  # Better device handling
+            )
+            return pipeline(
+                "text-generation",
+                model=model,
+                tokenizer=tokenizer,
+                max_new_tokens=512,
+                temperature=0.7,  # Add temperature for better generation
+                do_sample=True,   # Enable sampling
+                top_p=0.95        # Add top_p for better text quality
+            )
+        except Exception as e:
+            st.error(f"Failed to initialize the model: {str(e)}")
+            return None
 
     text_gen_pipeline = initialize_pipeline(access_token)
 
     @st.cache_resource
-    def initialize_chain():
-        memory = ConversationBufferMemory()
-        return ConversationChain(llm=text_gen_pipeline, memory=memory)  # No LLM; handled by pipeline
-
-    conversation_chain = initialize_chain()
+    def initialize_memory():
+        return ConversationBufferMemory(
+            input_key="input",
+            output_key="output",
+            return_messages=True
+        )
 
     # Input job description
     job_description = st.text_area("Enter the job description:", "")
@@ -83,27 +96,51 @@ if access_token:
     # Display generated email
     if st.button("Generate Email"):
         if st.session_state.parsed_cv and job_description.strip():
-            # Prompt for email generation
-            prompt = (
-                f"Based on the following CV details:\n\n{st.session_state.parsed_cv}\n\n"
-                f"And the following job description:\n\n{job_description}\n\n"
-                f"Write a professional email expressing interest in the job. "
-                f"Make it concise, polite, and tailored to the job."
-            )
-
-            # Generate email using Hugging Face pipeline
-            response = text_gen_pipeline(prompt)[0]['generated_text']
-
-            # Update memory with job description and response
-            conversation_chain.memory.save_context({"job_description": job_description}, {"email": response})
-
-            # Display response
-            st.subheader("Generated Email:")
-            st.write(response)
-
-            # Display conversation history
-            st.subheader("History:")
-            st.write(conversation_chain.memory.buffer)
+            try:
+                memory = initialize_memory()
+                
+                # Improved prompt template
+                prompt = f"""Task: Write a professional job application email.
+
+CV Summary:
+{st.session_state.parsed_cv}
+
+Job Description:
+{job_description}
+
+Instructions: Write a concise and professional email expressing interest in the position. 
+Highlight relevant experience and skills from the CV that match the job requirements.
+Keep the tone professional and enthusiastic.
+
+Email:
+"""
+                
+                # Generate email using the pipeline
+                if text_gen_pipeline:
+                    response = text_gen_pipeline(
+                        prompt,
+                        clean_up_tokenization_spaces=True,
+                        return_full_text=False
+                    )[0]['generated_text']
+
+                    # Store in memory
+                    memory.save_context(
+                        {"input": f"Job Description: {job_description}"},
+                        {"output": response}
+                    )
+
+                    # Display response
+                    st.subheader("Generated Email:")
+                    st.write(response)
+
+                    # Display conversation history
+                    st.subheader("Previous Generations:")
+                    for entry in memory.load_memory_variables({})['history']:
+                        st.write(entry)
+                else:
+                    st.error("Text generation pipeline not properly initialized.")
+            except Exception as e:
+                st.error(f"Error generating email: {str(e)}")
         else:
             st.warning("Please upload your CV in the sidebar and enter a job description.")
 else:

requirements.txt

@@ -1,8 +1,8 @@
 # add requirements
-streamlit
-python-dotenv
-langchain
-transformers
-torch
-PyPDF2
+streamlit>=1.24.0
+python-dotenv>=0.19.0
+langchain>=0.1.0
+transformers>=4.36.0
+torch>=2.0.0
+PyPDF2>=3.0.0