Upload 17 files

.gitattributes

@@ -0,0 +1,44 @@
+db/ filter=lfs diff=lfs merge=lfs -text
+# LaMini-T5-738M/ filter=lfs diff=lfs merge=lfs -text
+*.sqlite3 filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+# HF
+*.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
+*.pdf filter=lfs diff=lfs merge=lfs -text
+*.pickel filter=lfs diff=lfs merge=lfs -text
+db/*.pickle filter=lfs diff=lfs merge=lfs -text
+db/c811917d-8276-48ba-b913-6ed6196f4484/index_metadata.pickle filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,5 @@
+__pycache__/
+# Lib/
+search_pdf_env/
+LaMini-T5-738M/
+# db/

Commands.txt

@@ -0,0 +1,17 @@
+Youtube video : https://youtu.be/rIV1EseKwU4?si=YOJ2a_9eYVPhxn6X
+Github : https://github.com/AIAnytime/Search-Your-PDF-App/tree/main
+LLM : https://huggingface.co/MBZUAI/LaMini-T5-738M
+
+
+NOTE: Remove the chroma settings from the code to work with latest versions
+
+
+
+1) Creating a virtual env
+python -m venv <env_name>
+
+2) Activating virtual environment
+search_pdf_env\Scripts\activate
+
+3)Installing requirements:
+pipi nstall -r requirements.txt

README.md

@@ -1,27 +1,10 @@
----
-license: mit
-title: Chat With Doc
-sdk: streamlit
-emoji: 🏃
-colorFrom: gray
-colorTo: pink
----
 metadata
-
 title: Chat With Doc
-
 emoji: 😻
-
 colorFrom: gray
-
 colorTo: pink
-
 sdk: streamlit
-
 sdk_version: 1.29.0
-
 app_file: app.py
-
 pinned: false
-
 license: mit

app.ipynb

@@ -0,0 +1,59 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -r requirements.txt\n",
+    "!pip install pyngrok"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!streamlit run app.py &>\"/content/drive/MyDrive/Colab Notebooks/LangChatbot/MAIN PROJECT - Langchain - STREAMLIT/KEFY_BOT_Langchain_streamlit/logs_streamlit.txt\" &\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ngrok config add-authtoken 2Z7XecBchSB7U8OxYamQIBoDH4F_7huod8eqNPzz6W5hgu1Uz"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pyngrok import ngrok\n",
+    "ngrok_tunnel = ngrok.connect(8502)\n",
+    "print('Public URL:', ngrok_tunnel.public_url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ngrok.kill()"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,86 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import pipeline
+import torch
+import base64
+import textwrap
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+
+@st.cache_resource
+def get_model():
+    # device = torch.device('cpu')
+    device = torch.device('cuda:0')
+
+    checkpoint = "LaMini-T5-738M"
+    checkpoint = "MBZUAI/LaMini-T5-738M"
+    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+    base_model = AutoModelForSeq2SeqLM.from_pretrained(
+        checkpoint,
+        device_map=device,
+        torch_dtype = torch.float32,
+        # offload_folder= "/model_ck"
+    )
+    return base_model,tokenizer
+
+@st.cache_resource
+def llm_pipeline():
+    base_model,tokenizer = get_model()
+    pipe = pipeline(
+        'text2text-generation',
+        model = base_model,
+        tokenizer=tokenizer,
+        max_length = 256,
+        do_sample = True,
+        temperature = 0.3,
+        top_p = 0.95,
+        device=device
+    )
+
+    local_llm = HuggingFacePipeline(pipeline = pipe)
+    return local_llm
+
+@st.cache_resource
+def qa_llm():
+    llm = llm_pipeline()
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    db = Chroma(persist_directory="db", embedding_function = embeddings)
+    retriever = db.as_retriever()
+    qa = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type = "stuff",
+        retriever = retriever,
+        return_source_documents=True
+    )
+    return qa
+
+
+def process_answer(instruction):
+    response=''
+    instruction = instruction
+    qa = qa_llm()
+    generated_text = qa(instruction)
+    answer = generated_text['result']
+    return answer, generated_text
+
+def main():
+    st.title("Search your pdf📚")
+    with st.expander("About the App"):
+        st.markdown(
+    """This is a Generative AI powered Question and Answering app that responds to questions about your PDF file.
+    """
+        )
+
+    question = st.text_area("Enter Your Question")
+    if st.button("Search"):
+        st.info("Your question: "+question)
+        st.info("Your Answer")
+        answer, metadata = process_answer(question)
+        st.write(answer)
+        st.write(metadata)
+
+
+if __name__ == "__main__":
+    main()

chatbot.py

@@ -0,0 +1,102 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import pipeline
+import torch
+import base64
+import textwrap
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+from streamlit_chat import message
+
+# device = torch.device('cpu')
+device = torch.device('cuda:0')
+
+
+checkpoint = "LaMini-T5-738M"
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+base_model = AutoModelForSeq2SeqLM.from_pretrained(
+    checkpoint,
+    device_map=device,
+    torch_dtype = torch.float32,
+    # offload_folder= "/model_ck"
+)
+
+@st.cache_resource
+def llm_pipeline():
+    pipe = pipeline(
+        'text2text-generation',
+        model = base_model,
+        tokenizer=tokenizer,
+        max_length = 256,
+        do_sample = True,
+        temperature = 0.3,
+        top_p = 0.95,
+    )
+
+    local_llm = HuggingFacePipeline(pipeline = pipe)
+    return local_llm
+
+@st.cache_resource
+def qa_llm():
+    llm = llm_pipeline()
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    db = Chroma(persist_directory="db", embedding_function = embeddings)
+    retriever = db.as_retriever()
+    qa = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type = "stuff",
+        retriever = retriever,
+        return_source_documents=True
+    )
+    return qa
+
+
+def process_answer(instruction):
+    response=''
+    instruction = instruction
+    qa = qa_llm()
+    generated_text = qa(instruction)
+    answer = generated_text['result']
+    return answer, generated_text
+
+# Display conversation history using Streamlit messages
+def display_conversation(history):
+    for i in range(len(history["generated"])):
+        message(history["past"][i] , is_user=True, key= str(i) + "_user")
+        message(history["generated"][i] , key= str(i))
+
+
+def main():
+    st.title("Chat with your pdf📚")
+    with st.expander("About the App"):
+        st.markdown(
+        """
+        This is a Generative AI powered Question and Answering app that responds to questions about your PDF file.
+        """
+        )
+
+    user_input = st.text_input("",key="input")
+
+    # Initialize session state for generated responses and past messages
+    if "generated" not in st.session_state:
+        st.session_state["generated"] = ["I am ready to help you"]
+    if "past" not in st.session_state:
+        st.session_state["past"] = ["Hey There!"]
+
+    # Search the database for a response based on user input and update session state
+    if user_input:
+        answer = process_answer({"query" : user_input})
+        st.session_state["past"].append(user_input)
+        response = answer
+        st.session_state["generated"].append(response)
+
+    # Display Conversation history using Streamlit messages
+    if st.session_state["generated"]:
+        display_conversation(st.session_state)
+    
+
+
+if __name__ == "__main__":
+    main()

constants.py

@@ -0,0 +1,9 @@
+import os
+from chromadb.config import Settings
+
+# Define Chroma Settings
+CHROMA_SETTINGS = Settings(
+    chroma_db_impl = 'duckdb+parquet' ,
+    persist_directory = "db",
+    anonymized_telemetry = False
+)

db/c811917d-8276-48ba-b913-6ed6196f4484/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0656652b4f3db81247ca6f4a0365416da3b66a0ed0cd46e9392400ee92da06ef
+size 62012000

db/c811917d-8276-48ba-b913-6ed6196f4484/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c6e025ebb371f800e844ce62d9b7dde9b123633b5d9e3bf6199de9a6580582
+size 100

db/c811917d-8276-48ba-b913-6ed6196f4484/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b13caae7bf03a47b0bc51c04f39eb07ffdc234fe6b7f369b872a2447117da8
+size 2144478

db/c811917d-8276-48ba-b913-6ed6196f4484/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4fd7fddbb7246719bc06423736fe0cebe9b417bdb555ae72f6061248bc1e995
+size 148000

db/c811917d-8276-48ba-b913-6ed6196f4484/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbff72c999b684e5ef2d0dfbeb81e5179ca48fa5c62b8ccadf3ef53f2561744
+size 317184

db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5ae7212513205065174fc77e7fd813e803de0635f4fb32947eeeb2fbb067cf
+size 264290304

docs/Alfred V. Aho, Monica S. Lam, Ravi Sethi, Jeffrey D. Ullman-Compilers - Principles, Techniques, and Tools-Pearson_Addison Wesley (2006).pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92646e7788a17653fbcd9aaf16724ae62e67b4990f4289ee39ca55e5fb9ab62a
+size 6060190

ingest.py

@@ -0,0 +1,27 @@
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader, PDFMinerLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma
+import os
+from constants import CHROMA_SETTINGS
+
+persist_directory = "db"
+
+def main():
+    for root, dirs, files in os.walk("docs"):
+        for file in files:
+            if file.endswith(".pdf"):
+                print(file)
+                loader = PDFMinerLoader(os.path.join(root, file))
+                documents = loader.load()
+                text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=500)
+                texts = text_splitter.split_documents(documents)
+                # create embeddings 
+                embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+                # create vector store
+                db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory)
+                db.persist()
+                db=None
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,18 @@
+langchain
+streamlit
+transformers
+requests
+torch
+einops
+accelerate
+bitsandbytes
+pdfminer.six
+bs4
+sentence-transformers
+chromadb
+torchvision
+torchaudio
+sentencepiece
+requests
+uvicorn
+streamlit-chat