Duplicate from lavanjv/naturalremedybot

.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

Dockerfile

@@ -0,0 +1,35 @@
+# Use the official Python image as the base image
+FROM python:3.10
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Create a non-root user
+RUN useradd -ms /bin/bash myuser
+
+# Give the user ownership of the working directory and home directory
+RUN chown -R myuser:myuser /app /home/myuser
+
+# Switch to the non-root user
+USER myuser
+
+# Copy the entire contents of the local directory into the container
+COPY . .
+
+# Download the model file
+RUN wget https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/resolve/main/llama-2-7b-chat.ggmlv3.q8_0.bin
+
+# Install chainlit and add it to PATH
+RUN pip install chainlit --user
+
+# Set the PATH to include user-specific binaries
+ENV PATH="/home/myuser/.local/bin:${PATH}"
+
+# Install the required Python packages
+RUN pip install -r requirements.txt
+
+# Expose port 7860 internally in the container
+EXPOSE 7860
+
+# Run the ChainlIt command
+CMD ["chainlit", "run", "model.py", "-w", "--port", "7860"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Naturalremedybot
+emoji: 😻
+colorFrom: red
+colorTo: red
+sdk: docker
+pinned: false
+duplicated_from: lavanjv/naturalremedybot
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

chainlit.md

@@ -0,0 +1,11 @@
+# Welcome to Llama2 Med-Bot! 🚀🤖
+
+Hi there, 👋 We're excited to have you on board. This is a powerful bot designed to help you ask queries related to your data/knowledge.
+
+## Useful Links 🔗
+
+- **Data:** This is the data which has been used as a knowledge base. [Knowledge Base](https://docs.chainlit.io) 📚
+- **Join AI Anytime Community:** Join our friendly [WhatsApp Group](https://discord.gg/ZThrUxbAYw) to ask questions, share your projects, and connect with other developers! 💬
+
+Happy chatting! 💻😊
+

ingest.py

@@ -0,0 +1,28 @@
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter 
+
+DATA_PATH = 'data/'
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+# Create vector database
+def create_vector_db():
+    loader = DirectoryLoader(DATA_PATH,
+                             glob='*.pdf',
+                             loader_cls=PyPDFLoader)
+
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500,
+                                                   chunk_overlap=50)
+    texts = text_splitter.split_documents(documents)
+
+    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',
+                                       model_kwargs={'device': 'cpu'})
+
+    db = FAISS.from_documents(texts, embeddings)
+    db.save_local(DB_FAISS_PATH)
+
+if __name__ == "__main__":
+    create_vector_db()
+

model.py

@@ -0,0 +1,95 @@
+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():
+    # Load the locally downloaded model here
+    llm = CTransformers(
+        model = "llama-2-7b-chat.ggmlv3.q8_0.bin",
+        model_type="llama",
+        max_new_tokens = 512,
+        temperature = 0.5
+    )
+    return llm
+
+#QA Model Function
+def qa_bot():
+    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()
+    qa_prompt = set_custom_prompt()
+    qa = retrieval_qa_chain(llm, qa_prompt, db)
+
+    return qa
+
+#output function
+def final_result(query):
+    qa_result = qa_bot()
+    response = qa_result({'query': query})
+    return response
+
+#chainlit code
+@cl.on_chat_start
+async def start():
+    chain = qa_bot()
+    msg = cl.Message(content="Starting the bot...")
+    await msg.send()
+    msg.content = "Hi, Welcome to Medical Bot. What is your query?"
+    await msg.update()
+
+    cl.user_session.set("chain", chain)
+
+@cl.on_message
+async def main(message):
+    chain = cl.user_session.get("chain") 
+    cb = cl.AsyncLangchainCallbackHandler(
+        stream_final_answer=True, answer_prefix_tokens=["FINAL", "ANSWER"]
+    )
+    cb.answer_reached = True
+    res = await chain.acall(message, callbacks=[cb])
+    answer = res["result"]
+    sources = res["source_documents"]
+
+    if sources:
+        answer += f"\nSources:" + str(sources)
+    else:
+        answer += "\nNo sources found"
+
+    await cl.Message(content=answer).send()
+

requirements.txt

@@ -0,0 +1,9 @@
+pypdf
+langchain
+torch
+accelerate
+transformers
+sentence_transformers
+faiss_cpu
+chainlit
+ctransformers

vectorstore/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed7b526714fd31111a0aff4a0d7ac3c60d537fb991e1a0632c810c635fc6cf9
+size 3657261

vectorstore/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13614b35d8ae6db0bf0702c92735f8801ded062a97b53ab1f1dc2a1fb3e7781f
+size 1316371