Update file_utils.py

file_utils.py

@@ -15,7 +15,7 @@ SQLModel.metadata.create_all(engine)
 openai_api_key = os.getenv("OPENAI_API_KEY")
 client = OpenAI(api_key=openai_api_key)
 
-# === DB Table for Study Guides ===
+# === DB Tables ===
 class StudyGuideEntry(SQLModel, table=True):
     id: Optional[int] = Field(default=None, primary_key=True)
     user: str
@@ -23,7 +23,35 @@ class StudyGuideEntry(SQLModel, table=True):
     guide: str
     timestamp: str
 
-# === DB Utilities ===
+class UserFileEntry(SQLModel, table=True):
+    id: Optional[int] = Field(default=None, primary_key=True)
+    user: str
+    filename: str
+    file_path: str
+    timestamp: str
+
+SQLModel.metadata.create_all(engine)
+
+# === File Persistence ===
+def save_user_file(user, filename, file_path):
+    session = Session(engine)
+    entry = UserFileEntry(
+        user=user,
+        filename=filename,
+        file_path=file_path,
+        timestamp=datetime.now().strftime("%Y-%m-%d %H:%M")
+    )
+    session.add(entry)
+    session.commit()
+    session.close()
+
+def fetch_user_files(user):
+    session = Session(engine)
+    statement = select(UserFileEntry).where(UserFileEntry.user == user)
+    results = session.exec(statement).all()
+    session.close()
+    return results
+
 def save_study_guide(user, filename, guide):
     session = Session(engine)
     entry = StudyGuideEntry(
@@ -43,31 +71,14 @@ def fetch_study_guides(user):
     session.close()
     return results
 
-# === GPT Utility ===
+# === LLM Core ===
 def call_llm(prompt=None, system_message="You are a helpful assistant.", messages=None):
-    """
-    Call GPT-4 with either a single prompt or full message history.
-    Handles token limits and returns a single string response.
-
-    Args:
-        prompt (str): Optional one-turn prompt.
-        system_message (str): Optional system message.
-        messages (list): Optional list of chat messages (for multi-turn chat).
-
-    Returns:
-        str: The assistant's reply.
-    """
-    max_tokens = 8192
-    max_safe_chars = 28000  # Roughly ~7000 tokens
-
+    max_safe_chars = 28000
     if messages:
-        # Optional: truncate text-heavy messages
         for msg in messages:
             if len(msg["content"]) > max_safe_chars:
                 msg["content"] = msg["content"][:max_safe_chars] + "\n\n[Truncated due to token limit]"
-
     else:
-        # One-shot prompt mode
         if prompt and len(prompt) > max_safe_chars:
             prompt = prompt[:max_safe_chars] + "\n\n[Truncated due to token limit]"
         messages = [
@@ -80,48 +91,45 @@ def call_llm(prompt=None, system_message="You are a helpful assistant.", message
         messages=messages,
         temperature=0.7
     )
-
     return response.choices[0].message.content
 
-
 # === File Parsing ===
 def extract_text_from_file(file):
     ext = os.path.splitext(file.name)[1].lower()
-
     if ext == ".pdf":
         with fitz.open(file.name) as doc:
             return "\n".join([page.get_text() for page in doc])
-
     elif ext in [".txt", ".md"]:
         return file.read().decode("utf-8")
-
     elif ext == ".pptx":
         prs = Presentation(file.name)
         return "\n".join([
             shape.text for slide in prs.slides for shape in slide.shapes if hasattr(shape, "text")
         ])
-
     else:
         return "Unsupported file type."
 
 # === GPT-Based Generators ===
-
 def generate_summary(text):
     prompt = f"Summarize the following document in 5–7 bullet points:\n\n{text}"
-    return call_llm(prompt)
+    return call_llm(prompt=prompt)
 
 def generate_flashcards(text):
-    prompt = f"Generate 5 flashcards based on this document. Each flashcard should follow this format:\nQ: ...\nA: ...\n\n{text}"
-    return call_llm(prompt)
+    prompt = (
+        "Generate 5 flashcards based on the document below.\n"
+        "Each flashcard should follow this format:\nQ: <question>\nA: <answer>\n\n"
+        f"{text}"
+    )
+    return call_llm(prompt=prompt)
 
 def generate_quiz(text):
     prompt = (
-        "Generate 5 multiple choice questions based on the document below. "
-        "Return the result as a JSON array where each item has:\n"
+        "Generate 5 multiple choice questions from the document below. "
+        "Return a JSON array where each item has:\n"
         "- question (string)\n- options (list of strings)\n- answer (correct option string)\n\n"
         f"{text}"
     )
-    response = call_llm(prompt)
+    response = call_llm(prompt=prompt)
     try:
         return json.loads(response)
     except:
@@ -129,4 +137,4 @@ def generate_quiz(text):
 
 def answer_question(text, question):
     prompt = f"Using only the document below, answer this question:\n\nDocument:\n{text}\n\nQuestion:\n{question}"
-    return call_llm(prompt)
+    return call_llm(prompt=prompt)