deployment config

.gitignore

@@ -1,7 +1,5 @@
 venv
-InternTaskGenAI.pdf
 .env
 research_assistant.db
-neural computing cwsi.pdf
 app.log
 __pycache__

DockerFile

@@ -0,0 +1,19 @@
+FROM python:3.10
+
+WORKDIR /app
+
+
+COPY backend /app/backend
+COPY frontend /app/frontend
+
+
+COPY requirements.txt /app/requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+
+COPY start.sh /app/start.sh
+RUN chmod +x /app/start.sh
+
+EXPOSE 7860
+
+CMD ["/app/start.sh"]

README.md

@@ -1,3 +1,13 @@
+---
+title: Smart Research Assistant
+emoji: 🔥
+colorFrom: green
+colorTo: yellow
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 # smart-research-assistant
 
 ## TODO:

app.py

@@ -1,5 +0,0 @@
-from backend.pinecone_utilis import create_pinecone_vectorstore,load_and_split_document, index_document_to_pinecone
-
-file_path="InternTaskGenAI.pdf"
-
-print(index_document_to_pinecone(file_path=file_path, file_id=1))

backend/db_utils.py

@@ -25,6 +25,7 @@ def create_document_store():
     conn = get_db_connection()
     conn.execute('''CREATE TABLE IF NOT EXISTS document_store
                     (id INTEGER PRIMARY KEY AUTOINCREMENT,
+                     session_id TEXT,
                      filename TEXT,
                      content TEXT,
                      upload_timestamp TIMESTAMP DEFAULT CURRENT_TIMESTAMP)''')
@@ -48,10 +49,11 @@ def get_chat_history(session_id):
 
     conn.close()
     return messages
-def insert_document_record(filename, content):
+def insert_document_record(session_id, filename, content):
     conn = get_db_connection()
     cursor = conn.cursor()
-    cursor.execute('INSERT INTO document_store (filename, content) VALUES (?, ?)', (filename, content))
+    cursor.execute('INSERT INTO document_store (session_id, filename, content) VALUES (?, ?, ?)', 
+                   (session_id, filename, content))
     file_id = cursor.lastrowid
     conn.commit()
     conn.close()
@@ -64,10 +66,10 @@ def delete_document_record(file_id):
     conn.close()
     return True
 
-def get_all_documents():
+def get_all_documents(session_id):
     conn = get_db_connection()
     cursor = conn.cursor()
-    cursor.execute('SELECT id, filename, upload_timestamp FROM document_store ORDER BY upload_timestamp DESC')
+    cursor.execute('SELECT id, filename, upload_timestamp FROM document_store WHERE session_id = ? ORDER BY upload_timestamp DESC', (session_id,))
     documents = cursor.fetchall()
     conn.close()
     return [dict(doc) for doc in documents]

backend/main.py

@@ -1,4 +1,4 @@
-from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi import FastAPI, File, UploadFile, HTTPException, Form
 from backend.pydantic_models import QueryInput, QueryResponse, DocumentInfo, DeleteFileRequest, ChallengeRequest, EvaluateAnswer
 from backend.langchain_utils import generate_response, retrieve
 from backend.db_utils import insert_application_logs, get_chat_history, get_all_documents, insert_document_record, delete_document_record, get_file_content
@@ -99,7 +99,9 @@ def evaluate_response(request: EvaluateAnswer):
 
 
 @app.post("/upload-doc")
-def upload_and_index_document(file: UploadFile = File(...)):
+def upload_and_index_document(file: UploadFile = File(...), session_id: str = Form(None)):
+    if not session_id:
+        session_id = str(uuid.uuid4())
     allowed_extensions = ['.pdf', '.txt']
     file_extension = os.path.splitext(file.filename)[1].lower()
 
@@ -114,7 +116,7 @@ def upload_and_index_document(file: UploadFile = File(...)):
             shutil.copyfileobj(file.file, buffer)
         docs = load_and_split_document(temp_file_path)
         docs_content = "\n\n".join(doc.page_content for doc in docs)
-        file_id = insert_document_record(file.filename, docs_content)
+        file_id = insert_document_record(session_id, file.filename, docs_content)
         success = index_document_to_pinecone(temp_file_path, file_id)
 
         if success:
@@ -144,8 +146,8 @@ def upload_and_index_document(file: UploadFile = File(...)):
             os.remove(temp_file_path)
 
 @app.get("/list-docs", response_model=list[DocumentInfo])
-def list_documents():
-    return get_all_documents()
+def list_documents(session_id: str):
+    return get_all_documents(session_id)
 
 @app.post("/delete-doc")
 def delete_document(request: DeleteFileRequest):

frontend/app.py

@@ -32,7 +32,8 @@ with st.sidebar:
         if st.button("Upload Document"):
             response = requests.post(
                 f"{BACKEND_URL}/upload-doc",
-                files={"file": (uploaded_file.name, uploaded_file, "application/octet-stream")}
+                files={"file": (uploaded_file.name, uploaded_file, "application/octet-stream")},
+                data={"session_id": st.session_state.session_id}
             )
             if response.status_code == 200:
                 data = response.json()
@@ -46,7 +47,7 @@ with st.sidebar:
     # List documents
     st.subheader("Uploaded Documents")
     try:
-        documents = requests.get(f"{BACKEND_URL}/list-docs").json()
+        documents = requests.get(f"{BACKEND_URL}/list-docs", params={"session_id": st.session_state.session_id}).json()
         for doc in documents:
             doc_id = doc["id"]
             with st.container(border=True):

start.sh

@@ -0,0 +1,8 @@
+#!/bin/sh
+
+
+cd /app/backend && uvicorn main:app --host 0.0.0.0 --port 8000 &
+
+
+cd /app/frontend && streamlit run ui.py --server.port=7860 --server.address=0.0.0.0
+

test.py

@@ -1,25 +0,0 @@
-
-import requests
-
-# Set the FastAPI backend URL
-BASE_URL = "http://localhost:8000"
-
-
-# with open("neural computing cwsi.pdf", "rb") as f:
-#     files = {"file": ("neural computing cwsi.pdf", f, "text/plain")}
-#     upload_response = requests.post(f"{BASE_URL}/upload-doc", files=files)
-# # print("Upload Response:", upload_response.json())
-
-# file_id = upload_response.json().get("summary")
-
-# print(file_id)
-
-chat_data = {"question": "What is the main topic?", "model": "gpt-4o-mini"}
-chat_response = requests.post(f"{BASE_URL}/chat", json=chat_data)
-print("Chat Response:", chat_response.json())
-
-# delete_data={"file_id": 1}
-
-# delete_response = requests.post(f"{BASE_URL}/delete-doc", json=delete_data)
-
-# print("Delete Response:", delete_response.json())