Basic version with llama2-7b

.gitattributes

@@ -33,3 +33,4 @@ 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
+AstroBot/vectorstore/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

AstroBot/.chainlit/config.toml

@@ -0,0 +1,63 @@
+[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
+
+[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 = ""
+
+# 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 = "0.6.2"

AstroBot/README.md

@@ -0,0 +1,2 @@
+# Astrobot
+An AI powered chatbot based on llama2 for answering your questions related to astronomy and astrophysics.

AstroBot/chainlit.md

@@ -0,0 +1,4 @@
+# Welcome to AstroBot! 🚀🤖
+
+Hi there! 👋 I am AstroBot - a locally-hosted astronomy chatbot designed to answer your questions in the field of astronomy!
+

AstroBot/load.py

@@ -0,0 +1,27 @@
+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 = 'Files/'
+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()

AstroBot/model.py

@@ -0,0 +1,94 @@
+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 questions.
+If you don't know the answer, just say that you don't know, but 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 AstroBot. 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()

AstroBot/requirements.txt

@@ -0,0 +1,11 @@
+pypdf
+langchain
+torch
+accelerate
+bitsandbytes
+transformers
+sentence_transformers
+faiss_cpu
+chainlit
+ctransformers
+protobuf==3.20.*

AstroBot/vectorstore/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6caa034bb007e2add887fe4566d2ad634be7a2823e58a2725f1b5ec6a85be251
+size 7620141

AstroBot/vectorstore/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c32c83481ebbdb462d24bcb194dab3e4d1b9865aa495def7f2cdadb8f326ef
+size 2725130