Upload 6 files

.gitattributes

@@ -33,3 +33,5 @@ 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/71763-gale-encyclopedia-of-medicine.-vol.-1.-2nd-ed.pdf filter=lfs diff=lfs merge=lfs -text
+vectorstore/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

data/71763-gale-encyclopedia-of-medicine.-vol.-1.-2nd-ed.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753cd53b7a3020bbd91f05629b0e3ddcfb6a114d7bbedb22c2298b66f5dd00cc
+size 16127037

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()
+

model.py

@@ -0,0 +1,95 @@
+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
+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 = 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: 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()
+

requirements.txt

@@ -0,0 +1,11 @@
+pypdf
+langchain
+torch
+accelerate
+bitsandbytes
+ctransformers
+sentence_transformers
+faiss_cpu
+chainlit
+huggingface_hub
+langchain_community

vectorstore/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c219be0c422137d6354fdf0db6f2a2fe719ba536215b2dcba2366723f00b6e9
+size 10983981

vectorstore/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75f6e95d75f5bad95668fcd18f2daffb0d562d33784e6228e5c0f785605ee0c
+size 3567746