Add medical chabot

demos/medical-chatbot/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 AI Anytime
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

demos/medical-chatbot/README.md

@@ -0,0 +1,16 @@
+# MPT-Medical-Chatbot
+This is a medical bot built using MPT and Sentence Transformers. The bot is powered by DeepSparse, Langchain, and Chainlit. The bot runs on a decent CPU machine with a minimum of 16GB of RAM.
+
+## Installation
+
+```bash
+pip install -r requrements.txt
+```
+
+## Start with Chainlit
+
+```bash
+MODEL_PATH="hf:neuralmagic/mpt-7b-chat-pruned50-quant" chainlit run model.py -w
+```
+
+<img width="1350" alt="Screenshot 2023-08-13 at 7 12 54 PM" src="https://github.com/mgoin/MPT-Medical-Chatbot/assets/3195154/6841439d-0f27-42d6-af15-65a36e2f0a87">

demos/medical-chatbot/chainlit.md

@@ -0,0 +1,12 @@
+# Welcome to MPT 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 🔗
+
+- **DeepSparse:** This is the [inference engine](https://github.com/neuralmagic/deepsparse) powering the sparse LLM in this demo!
+- **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! 💻😊
+

demos/medical-chatbot/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()
+

demos/medical-chatbot/model.py

@@ -0,0 +1,109 @@
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.prompts import PromptTemplate
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+import chainlit as cl
+from langchain.llms import DeepSparse
+import os
+
+MODEL_PATH = os.environ.get("MODEL_PATH") or "hf:neuralmagic/mpt-7b-chat-pruned50-quant"
+
+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:
+"""
+
+
+# Loading the model
+def load_llm():
+    # Load the locally downloaded model here
+    llm = DeepSparse(
+        model=MODEL_PATH,
+        model_config={"sequence_length": 2048, "trust_remote_code": True},
+        generation_config={"max_new_tokens": 300},
+    )
+    return llm
+
+
+llm = load_llm()
+
+
+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
+
+
+# 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)
+    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: cl.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.content, 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()

demos/medical-chatbot/requirements.txt

@@ -0,0 +1,9 @@
+pypdf
+langchain
+torch
+transformers
+datasets
+sentence_transformers
+faiss_cpu
+chainlit
+deepsparse-nightly[llm]