Upload 7 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY = "AIzaSyDUeED6C6qepr7gQtmfyPza5nMjQbhbaOw"

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+.env
+.gitignore

README.md

@@ -1,12 +1,12 @@
----
-title: Chatbot
-emoji: 🏆
-colorFrom: pink
-colorTo: red
-sdk: streamlit
-sdk_version: 1.44.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Chatbot
+emoji: 🏆
+colorFrom: pink
+colorTo: red
+sdk: streamlit
+sdk_version: 1.44.1
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,87 +1,87 @@
-import streamlit as st
-from langchain.document_loaders import PyPDFLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import Chroma
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.chains import RetrievalQA
-from langchain_google_genai import ChatGoogleGenerativeAI
-import tempfile
-import os
-from dotenv import load_dotenv
-from pydantic import SecretStr
-
-
-load_dotenv()
-GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
-
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-
-# ---------------------------- SETUP ----------------------------
-
-st.title("📄 LangChain RAG Chatbot")
-
-# Session state
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = []
-
-if "qa_chain" not in st.session_state:
-    st.session_state.qa_chain = None
-
-# ---------------------------- FILE UPLOAD ----------------------------
-
-st.subheader("Upload your PDF")
-pdf_file = st.file_uploader("Upload", type="pdf")
-
-if pdf_file is not None and st.session_state.qa_chain is None:
-    with st.spinner("🔍 Processing document..."):
-        # Save file temporarily
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
-            tmp_file.write(pdf_file.read())
-            tmp_path = tmp_file.name
-
-        # Load and split PDF
-        loader = PyPDFLoader(tmp_path)
-        documents = loader.load_and_split()
-
-        splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-        chunks = splitter.split_documents(documents)
-
-        # Vector store
-        
-        vectordb = Chroma.from_documents(
-            chunks, embeddings, persist_directory="./chroma_db"
-        )
-        retriever = vectordb.as_retriever()
-
-        # QA Chain
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", api_key=SecretStr(GOOGLE_API_KEY) if GOOGLE_API_KEY else None)
-        qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
-
-        # Store in session
-        st.session_state.qa_chain = qa_chain
-        st.success("✅ Document processed and indexed!")
-
-# ---------------------------- CHAT ----------------------------
-
-if st.session_state.qa_chain:
-    st.subheader("💬 Ask a question")
-
-    question = st.text_input("You:", key="user_input")
-
-    if question:
-        with st.spinner("🤖 Generating answer..."):
-            answer = st.session_state.qa_chain.run(question)
-            st.session_state.chat_history.append({"user": question, "bot": answer})
-
-    # Display chat history
-    for chat in st.session_state.chat_history:
-        st.markdown(f"🧑 **You:** {chat['user']}")
-        st.markdown(f"🤖 **Bot:** {chat['bot']}")
-
-    # Reset button
-    if st.button("🔄 Reset Chat"):
-        st.session_state.chat_history = []
-        st.session_state.qa_chain = None
-        st.rerun()
-else:
-    st.info("📂 Please upload a PDF to begin.")
+import streamlit as st
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from langchain_google_genai import ChatGoogleGenerativeAI
+import tempfile
+import os
+from dotenv import load_dotenv
+from pydantic import SecretStr
+
+
+load_dotenv()
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+# ---------------------------- SETUP ----------------------------
+
+st.title("📄 LangChain RAG Chatbot")
+
+# Session state
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
+
+if "qa_chain" not in st.session_state:
+    st.session_state.qa_chain = None
+
+# ---------------------------- FILE UPLOAD ----------------------------
+
+st.subheader("Upload your PDF")
+pdf_file = st.file_uploader("Upload", type="pdf")
+
+if pdf_file is not None and st.session_state.qa_chain is None:
+    with st.spinner("🔍 Processing document..."):
+        # Save file temporarily
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+            tmp_file.write(pdf_file.read())
+            tmp_path = tmp_file.name
+
+        # Load and split PDF
+        loader = PyPDFLoader(tmp_path)
+        documents = loader.load_and_split()
+
+        splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        chunks = splitter.split_documents(documents)
+
+        # Vector store
+        
+        vectordb = Chroma.from_documents(
+            chunks, embeddings, persist_directory="./chroma_db"
+        )
+        retriever = vectordb.as_retriever()
+
+        # QA Chain
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", api_key=SecretStr(GOOGLE_API_KEY) if GOOGLE_API_KEY else None)
+        qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
+
+        # Store in session
+        st.session_state.qa_chain = qa_chain
+        st.success("✅ Document processed and indexed!")
+
+# ---------------------------- CHAT ----------------------------
+
+if st.session_state.qa_chain:
+    st.subheader("💬 Ask a question")
+
+    question = st.text_input("You:", key="user_input")
+
+    if question:
+        with st.spinner("🤖 Generating answer..."):
+            answer = st.session_state.qa_chain.run(question)
+            st.session_state.chat_history.append({"user": question, "bot": answer})
+
+    # Display chat history
+    for chat in st.session_state.chat_history:
+        st.markdown(f"🧑 **You:** {chat['user']}")
+        st.markdown(f"🤖 **Bot:** {chat['bot']}")
+
+    # Reset button
+    if st.button("🔄 Reset Chat"):
+        st.session_state.chat_history = []
+        st.session_state.qa_chain = None
+        st.rerun()
+else:
+    st.info("📂 Please upload a PDF to begin.")

app_bkp.py

@@ -1,68 +1,68 @@
-import streamlit as st
-from transformers import pipeline
-import fitz
-
-qa = pipeline("question-answering", model="deepset/roberta-base-squad2", device=0)
-text_gen = pipeline("text2text-generation", model="google/flan-t5-base", device=0)
-
-
-# extract text from uploaded document
-def extract_PDF(file):
-    text = ""
-    with fitz.open(stream=file.read(), filetype="pdf") as doc:
-        for page in doc:
-            text += page.get_text() # type: ignore
-    return text
-
-
-# ------------------------------------------------------------------------------
-
-# -----------------------------------Streamlit UI--------------------------------
-
-st.title("Chatbot with Huggingface")
-
-st.subheader("Upload file")
-pdf_file = st.file_uploader("Upload", type="pdf")
-
-# Initialize Session state for convo history
-
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = []
-
-if "context" not in st.session_state:
-    st.session_state.context = None
-
-# extract text and store in the session
-if pdf_file is not None and st.session_state.context is None:
-    st.session_state.context = extract_PDF(pdf_file)
-
-
-# Chat section
-
-if st.session_state.context:
-    st.subheader("Chat with the PDF")
-
-    question = st.text_input("You", key="user_input")
-
-    
-    if question:
-        result = qa(question=question, context=st.session_state.context) # type: ignore
-        
-        context_chunk = st.session_state.context[:1500]
-        prompt = f"Context: {context_chunk}\nQuestion: {question}\nAnswer:"
-        
-        generated = text_gen(prompt, max_length=100)[0]['generated_text']  # type: ignore
-
-        # save convo
-        st.session_state.chat_history.append(
-            {"user": question, "bot": generated}
-        )
-
-        # Display chat
-
-    for chat in st.session_state.chat_history:
-        st.markdown(f"**You:** {chat['user']}")
-        st.markdown(f"**Bot:** {chat['bot']}")
-
-else:
-    st.info("Please upload PDF to begin")
+import streamlit as st
+from transformers import pipeline
+import fitz
+
+qa = pipeline("question-answering", model="deepset/roberta-base-squad2", device=0)
+text_gen = pipeline("text2text-generation", model="google/flan-t5-base", device=0)
+
+
+# extract text from uploaded document
+def extract_PDF(file):
+    text = ""
+    with fitz.open(stream=file.read(), filetype="pdf") as doc:
+        for page in doc:
+            text += page.get_text() # type: ignore
+    return text
+
+
+# ------------------------------------------------------------------------------
+
+# -----------------------------------Streamlit UI--------------------------------
+
+st.title("Chatbot with Huggingface")
+
+st.subheader("Upload file")
+pdf_file = st.file_uploader("Upload", type="pdf")
+
+# Initialize Session state for convo history
+
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
+
+if "context" not in st.session_state:
+    st.session_state.context = None
+
+# extract text and store in the session
+if pdf_file is not None and st.session_state.context is None:
+    st.session_state.context = extract_PDF(pdf_file)
+
+
+# Chat section
+
+if st.session_state.context:
+    st.subheader("Chat with the PDF")
+
+    question = st.text_input("You", key="user_input")
+
+    
+    if question:
+        result = qa(question=question, context=st.session_state.context) # type: ignore
+        
+        context_chunk = st.session_state.context[:1500]
+        prompt = f"Context: {context_chunk}\nQuestion: {question}\nAnswer:"
+        
+        generated = text_gen(prompt, max_length=100)[0]['generated_text']  # type: ignore
+
+        # save convo
+        st.session_state.chat_history.append(
+            {"user": question, "bot": generated}
+        )
+
+        # Display chat
+
+    for chat in st.session_state.chat_history:
+        st.markdown(f"**You:** {chat['user']}")
+        st.markdown(f"**Bot:** {chat['bot']}")
+
+else:
+    st.info("Please upload PDF to begin")

requirements.txt

@@ -1,12 +1,13 @@
-streamlit
-openai
-langchain-google-genai
-langchain-core
-langchain-text-splitters
-transformers
-tf-keras
-langchain 
-chromadb 
-tiktoken 
-pypdf
+streamlit
+openai
+langchain-google-genai
+langchain-core
+langchain-community
+langchain-text-splitters
+transformers
+tf-keras
+langchain 
+chromadb 
+tiktoken 
+pypdf
 sentence-transformers