changes

app-backup.py

@@ -1,98 +0,0 @@
-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 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="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})
-    print(response)
-    return response
-
-
-# chain lit 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 Ryder 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 not sources:
-        answer += "\nNo sources found"
-
-    await cl.Message(content=answer).send()

app.py

@@ -1,29 +1,98 @@
+from langchain import PromptTemplate
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
-from langchain.document_loaders import PyPDFLoader, DirectoryLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.llms import CTransformers
+from langchain.chains import RetrievalQA
+import chainlit as cl
 
-DATA_PATH = 'data/'
 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.
 
-# Create vector database
-def create_vector_db():
-    loader = DirectoryLoader(DATA_PATH,
-                             glob='*.pdf',
-                             loader_cls=PyPDFLoader)
+Context: {context}
+Question: {question}
 
-    documents = loader.load()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500,
-                                                   chunk_overlap=50)
-    texts = text_splitter.split_documents(documents)
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""
 
-    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',
+
+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})
+    print(response)
+    return response
+
+
+# chain lit 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 Ryder Bot. What is your query?"
+    await msg.update()
+    cl.user_session.set("chain", chain)
+
 
-    db = FAISS.from_documents(texts, embeddings)
-    db.save_local(DB_FAISS_PATH)
+@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 not sources:
+        answer += "\nNo sources found"
 
-if __name__ == "__main__":
-    create_vector_db()
+    await cl.Message(content=answer).send()

ingest.py

@@ -0,0 +1,29 @@
+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()