Upload 14 files

.chainlit/config.toml

@@ -0,0 +1,72 @@
+[project]
+# If true (default), the app will be available to anonymous users.
+# If false, users will need to authenticate and be part of the project to use the app.
+public = true
+
+# The project ID (found on https://cloud.chainlit.io).
+# The project ID is required when public is set to false or when using the cloud database.
+#id = ""
+
+# Uncomment if you want to persist the chats.
+# local will create a database in your .chainlit directory (requires node.js installed).
+# cloud will use the Chainlit cloud database.
+# custom will load use your custom client.
+# database = "local"
+
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = true
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+# Chainlit server address
+# chainlit_server = ""
+
+[UI]
+# Name of the app and chatbot.
+name = "Chatbot"
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# Link to your github repo. This will add a github button in the UI's header.
+github = "https://github.com/ThisIs-Developer"
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+
+[meta]
+generated_by = "0.6.402"

.gitattributes

@@ -33,3 +33,8 @@ 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
+conversession[[:space:]]e.g/ChatBot[[:space:]]Conversession[[:space:]]img-3.pdf filter=lfs diff=lfs merge=lfs -text
+conversession[[:space:]]e.g/ChatBot[[:space:]]Conversession[[:space:]]img-3.png filter=lfs diff=lfs merge=lfs -text
+conversession[[:space:]]e.g/ChatBot[[:space:]]Conversession[[:space:]]vid.mp4 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
+vectorstores/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

chainlit.md

@@ -0,0 +1,8 @@
+# Llama-2-GGML Medical Chatbot! 🚀🤖
+
+Llama-2-GGML Medical Chatbot is a medical chatbot that uses the **Llama-2-7B-Chat-GGML** model which is a *large language model (LLM)* that has been fine-tuned on a dataset of medical text and PDF **"The GALE ENCYCLOPEDIA of MEDICINE"** is a comprehensive medical reference that provides information on a wide range of medical topics.
+### The chatbot is still under development
+## Useful Links 🔗
+
+- **Model:** Know more about model [Llama-2-7B-Chat-GGML](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML) 📚
+- **GitHub:** Check out the repository [ThisIs-Developer/Llama-2-GGML-Medical-Chatbot](https://github.com/ThisIs-Developer/Llama-2-GGML-Medical-Chatbot) feel free to commit in the github repo ! 💬

conversession e.g/ChatBot Conversession img-3.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c678b11a684144d33f839c9a108455f47c1c9d0ab96f7bb86a454bbc11df9b
+size 10246322

conversession e.g/ChatBot Conversession vid.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cd2ec7b5e1665a21a1020c2a9ef4f380266407845e39909665725fd4ab0536
+size 4579961

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 +1,23 @@
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+
+
+DATA_PATH="data/"
+DB_FAISS_PATH="vectorstores/db_faiss"
+
+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 +1,98 @@
+import asyncio
+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 = 'vectorstores/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
+async 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
+async def final_result(query):
+    qa_result = await qa_bot()
+    response = await qa_result({'query': query})
+    return response
+
+# chainlit code
+@cl.on_chat_start
+async def start():
+    chain = await 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()
+
+if __name__ == "__main__":
+    asyncio.run(cl.main())

requirements.txt

@@ -0,0 +1,11 @@
+pypdf==3.15.5
+accelerate==0.22.0
+bitsandbytes==0.41.1
+chainlit==0.6.402
+ctransformers==0.2.26
+faiss-cpu==1.7.4
+huggingface-hub==0.16.4
+langchain==0.0.281
+sentence-transformers==2.2.2
+torch==2.0.1
+transformers==4.33.0

vectorstores/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b1dd53e3fc2abc2535c8c24111b40ede2386c32a1604eaec17f3232646e7ee
+size 10983981

vectorstores/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4007c732db0ecbd2a226c55a6f83f1bb9bf8d899079a2e52b971f8da3d78cea5
+size 3567746