Upload 5 files

README.md

@@ -1,12 +1,14 @@
 ---
-title: PDFChat
-emoji: 💻
-colorFrom: pink
-colorTo: green
+title: Chat Pdf File Using Deepseek Llm
+emoji: 🚀
+colorFrom: purple
+colorTo: red
 sdk: streamlit
-sdk_version: 1.42.1
+sdk_version: 1.41.1
 app_file: app.py
 pinned: false
+license: mit
+short_description: This app uses DeepSeek R1 model for answering questions accu
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,115 @@
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import os
+from langchain_community.embeddings import HuggingFaceEmbeddings  # Using Hugging Face embeddings
+from langchain.vectorstores import FAISS
+from langchain_groq import ChatGroq
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+os.getenv("GROQ_API_KEY")
+
+def get_pdf_text(pdf_docs):
+    """Extracts text from uploaded PDF files."""
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text
+
+def get_text_chunks(text):
+    """Splits extracted text into manageable chunks."""
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+def get_vector_store(text_chunks):
+    """Creates and saves a FAISS vector store from text chunks."""
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")  # Using Hugging Face embeddings
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    vector_store.save_local("faiss_index")
+
+def get_conversational_chain():
+    """Sets up a conversational chain using Groq LLM."""
+    prompt_template = """
+    Answer the question as detailed as possible from the provided context. If the answer is not in
+    the provided context, just say, "answer is not available in the context." Do not provide incorrect answers.
+
+    Context:
+    {context}?
+
+    Question:
+    {question}
+
+    Answer:
+    """
+    
+    model = ChatGroq(
+        temperature=0.3,
+        model_name="deepseek-r1-distill-llama-70b",  # Using Mixtral model through Groq
+        groq_api_key=os.getenv("GROQ_API_KEY")
+    )
+    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    return chain
+
+def user_input(user_question):
+    """Handles user queries by retrieving answers from the vector store."""
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")  # Using Hugging Face embeddings
+
+    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+    docs = new_db.similarity_search(user_question)
+
+    chain = get_conversational_chain()
+
+    response = chain(
+        {"input_documents": docs, "question": user_question},
+        return_only_outputs=True
+    )
+
+    st.markdown(f"### Reply:\n{response['output_text']}")
+
+def main():
+    """Main function to run the Streamlit app."""
+    st.set_page_config(page_title="Chat PDF", page_icon=":books:", layout="wide")
+    st.title("Chat with PDF using DeepSeek Ai")
+    
+    st.sidebar.header("Upload & Process PDF Files")
+    st.sidebar.markdown(
+        "Using DeepSeek R1 model for advanced conversational capabilities.")
+    
+    with st.sidebar:
+        pdf_docs = st.file_uploader(
+            "Upload your PDF files:",
+            accept_multiple_files=True,
+            type=["pdf"]
+        )
+        if st.button("Submit & Process"):
+            with st.spinner("Processing your files..."):
+                raw_text = get_pdf_text(pdf_docs)
+                text_chunks = get_text_chunks(raw_text)
+                get_vector_store(text_chunks)
+                st.success("PDFs processed and indexed successfully!")
+
+    st.markdown(
+        "### Ask Questions from Your PDF Files :mag:\n"
+        "Once you upload and process your PDFs, type your questions below."
+    )
+
+    user_question = st.text_input("Enter your question:", placeholder="What do you want to know?")
+
+    if user_question:
+        with st.spinner("Fetching your answer..."):
+            user_input(user_question)
+
+    st.sidebar.info(
+        "**Note:** This app uses DeepSeek R1 model for answering questions accurately."
+    )
+
+if __name__ == "__main__":
+    main()

gitattributes

@@ -0,0 +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

gitignore

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

requirements.txt

@@ -0,0 +1,15 @@
+streamlit
+google-generativeai
+python-dotenv
+langchain
+PyPDF2
+chromadb
+faiss-cpu
+langchain_google_genai
+langchain-community
+langchain-groq 
+langchain-openai
+langchainhub
+pypdf
+transformers
+sentence-transformers