dockerfile and helpmate

Dockerfile

@@ -1,14 +1,26 @@
 # Use Python base image
 FROM python:3.9-slim
 
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
 # Set the working directory
-WORKDIR /app
+# WORKDIR /app
 
-# Copy project files to the container
-COPY . /app
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
 
-RUN useradd -m -u 1000 user
-USER user
+# Copy project files to the container
+# COPY . /app
 
 # Install dependencies
 RUN pip install --no-cache-dir -r requirements.txt
@@ -17,4 +29,4 @@ RUN pip install --no-cache-dir -r requirements.txt
 EXPOSE 8000
 
 # Command to run FastAPI with Uvicorn
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]

helpmate_ai.py

@@ -177,6 +177,31 @@ def rerank_with_cross_encoder(query, results_df, top_k=3):
 # top_docs = rerank_with_cross_encoder(results_df)
 # top_docs
 
+def generate_response(query, top_docs):
+    """
+    Generate a response using GPT-3.5's ChatCompletion based on the user query and retrieved information.
+    """
+    messages = f"""
+                Remember your system message and that you are a helpful assistant that extracts relevant information from insurance policy documents to answer user queries accurately and concisely.
+                Your task is to extract and present relevant information from the policy documents to answer the user’s query.
+                The document excerpts are provided in the dataframe '{top_docs}', with the actual policy text in the 'documents' column and metadata (page numbers) in the 'metadata' column.
+                The user input is: '{query}'
+                """
+
+    # response = openai.chat.completions.create (
+    #     model="gpt
+                  ### Your Task:-3.5-turbo",
+    #     messages=messages
+    # )
+    conversation = [{"role": "user", "parts": messages}] 
+
+    return conversation #response.choices[0].message.content.split('\n')
+
+# response = generate_response(query, top_docs)
+# print(query + '\n')
+# print("\n".join(response))
+
+