Duplicate from Sakil/LLM_Question_Answering_ChatBot

Co-authored-by: Sakil Ansari <Sakil@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+vectorstore/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: LLM Question Answering ChatBot
+emoji: 🐢
+colorFrom: indigo
+colorTo: red
+sdk: streamlit
+sdk_version: 1.25.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: Sakil/LLM_Question_Answering_ChatBot
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,85 @@
+import streamlit as st
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain import PromptTemplate
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.llms import CTransformers
+from langchain.chains import RetrievalQA
+import chainlit as cl
+
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+custom_prompt_template = """Use the following pieces of information to answer the user's question.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
+Context: {context}
+Question: {question}
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""
+
+def set_custom_prompt():
+    """
+    Prompt template for QA retrieval for each vectorstore
+    """
+    prompt = PromptTemplate(template=custom_prompt_template,
+                            input_variables=['context', 'question'])
+    return prompt
+
+# Retrieval QA Chain
+def retrieval_qa_chain(llm, prompt, db):
+    qa_chain = RetrievalQA.from_chain_type(llm=llm,
+                                           chain_type='stuff',
+                                           retriever=db.as_retriever(search_kwargs={'k': 2}),
+                                           return_source_documents=True,
+                                           chain_type_kwargs={'prompt': prompt}
+                                           )
+    return qa_chain
+
+# Loading the model
+def load_llm(max_new_tokens, temperature):
+    # Load the locally downloaded model here
+    llm = CTransformers(
+        model="llama-2-7b-chat.ggmlv3.q8_0.bin",
+        model_type="llama",
+        max_new_tokens=max_new_tokens,
+        temperature=temperature
+    )
+    return llm
+
+# QA Model Function
+def qa_bot(max_new_tokens, temperature):
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
+                                       model_kwargs={'device': 'cpu'})
+    db = FAISS.load_local(DB_FAISS_PATH, embeddings)
+    llm = load_llm(max_new_tokens, temperature)
+    qa_prompt = set_custom_prompt()
+    qa = retrieval_qa_chain(llm, qa_prompt, db)
+
+    return qa
+
+def main():
+    st.title("AI ChatBot LLM")
+
+    max_new_tokens = st.slider("Max New Tokens", min_value=1, max_value=1000, value=512)
+    temperature = st.slider("Temperature", min_value=0.1, max_value=1.0, step=0.1, value=0.5)
+
+    qa_result = qa_bot(max_new_tokens, temperature)
+
+    user_input = st.text_input("Enter your question:")
+    
+    if st.button("Ask"):
+        response = qa_result({'query': user_input})
+        answer = response["result"]
+        sources = response["source_documents"]
+
+        st.write("Answer:", answer)
+        if sources:
+            st.write("Sources:", sources)
+        else:
+            st.write("No sources found")
+    
+    if st.button("Clear"):
+        st.text_input("Enter your question:", value="")
+
+if __name__ == "__main__":
+    main()

llama-2-7b-chat.ggmlv3.q8_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfdde943555c78294626a6ccd40184162d066d39774bd2c98dae24943d32cc3
+size 7160799872

requirements.txt

@@ -0,0 +1,12 @@
+langchain
+torch
+accelerate
+bitsandbytes
+transformers
+sentence_transformers
+chainlit
+python-docx
+ctransformers
+sentence_transformers
+faiss_cpu
+chainlit

vectorstore/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15dfc240a44f43797648bb6de6747514335fc4f68d9da7d91d41c4a90c074726
+size 1729581

vectorstore/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96663f6513fb640bf3002df1298cb5a2b4c1dab63601b05e8d96a43f23e375ca
+size 650320