Upload 8 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+data/Color_Atlas_of_Hematology__Practical_Microsc.pdf filter=lfs diff=lfs merge=lfs -text
+data/Pathophysiology[[:space:]]of[[:space:]]Blood[[:space:]]Disorders[[:space:]]([[:space:]]PDFDrive[[:space:]]).pdf filter=lfs diff=lfs merge=lfs -text
+vectorstore/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

chainlit.md

@@ -0,0 +1,31 @@
+# Hematologist AI Assistant 🩸💉
+
+Welcome to the Hematologist AI Assistant! This AI assistant is designed to help users with inquiries related to hematology, including blood disorders, treatments, and medical advice.
+
+## Features
+🔍 **Question Answering:** Ask the AI assistant questions related to hematology, and it will provide relevant answers based on its knowledge base.
+
+💬 **Chat Interface:** Engage in a conversation with the AI assistant through a user-friendly chat interface.
+
+📚 **Knowledge Base:** The AI assistant is equipped with a comprehensive knowledge base on various hematological topics, ensuring accurate and helpful responses.
+
+🔒 **Privacy:** Your conversations with the AI assistant are kept private and confidential, adhering to strict privacy and security protocols.
+
+## How to Use
+1. **Accessing the AI Assistant:** Simply visit the web interface provided or integrate the AI assistant into your application using the provided API.
+
+2. **Asking Questions:** Type your questions or inquiries into the chat interface and press the send button. The AI assistant will process your query and provide a response.
+
+3. **Exploring Topics:** Feel free to explore different topics related to hematology by asking questions or engaging in conversations with the AI assistant.
+
+## Examples
+- "What are the symptoms of anemia?"
+- "How is leukemia diagnosed?"
+- "Can you explain the treatment options for sickle cell disease?"
+- "What are the risk factors for thrombocytopenia?"
+
+## Support
+If you encounter any issues or have any questions about the Hematologist AI Assistant, please feel free to [contact us](mailto:[email protected]).
+
+
+Happy chatting! 🩸💬

data/Color_Atlas_of_Hematology__Practical_Microsc.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aec234780c9ae39807c8c2e2da338ae863940fa8409a8e61c8119523af6c816
+size 5609324

data/Pathophysiology of Blood Disorders ( PDFDrive ).pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cb77dc79543e6f11cad423d6071d1cb5ca22fe5dab8965494720cad442419c
+size 40315767

ingest.py

@@ -0,0 +1,28 @@
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.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()
+    

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

model.py

@@ -0,0 +1,90 @@
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.prompts import PromptTemplate
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.llms import CTransformers
+from langchain.chains import RetrievalQA
+from sentence_transformers import SentenceTransformer
+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 = "TheBloke/Llama-2-7B-Chat-GGML",
+        model_type="llama",
+        max_new_tokens = 1024,
+        temperature = 0.01
+    )
+    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,allow_dangerous_deserialization=True)
+    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: 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"]
+    await cl.Message(content=answer).send()

vectorstore/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca20520da7c0a6bee9159af1d93a28f1509708c0ea46a9f2e7267e0862c0db4
+size 4457517

vectorstore/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef6aec5c8f60cb7c723cf9b0ad176351b20a02c7bf353ad706ce7d469b909cf
+size 1499176