Delete src

src/__init__.py

@@ -1,4 +0,0 @@
-from src.llama_call import llama_call
-from src.openai_call import openai_call
-
-__all__ = ["llama_call", "openai_call"]

src/helper.py

@@ -1,27 +0,0 @@
-from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.embeddings import HuggingFaceEmbeddings
-
-
-# Extract data from the PDF
-def load_pdf(data):
-    loader = DirectoryLoader(data, glob="*.pdf", loader_cls=PyPDFLoader)
-
-    documents = loader.load()
-
-    return documents
-
-
-# Create text chunks
-def text_split(extracted_data):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=20)
-    text_chunks = text_splitter.split_documents(extracted_data)
-
-    return text_chunks
-
-
-def download_hugging_face_embeddings():
-    embeddings = HuggingFaceEmbeddings(
-        model_name="sentence-transformers/all-MiniLM-L6-v2"
-    )
-    return embeddings

src/llama_call.py

@@ -1,59 +0,0 @@
-from src.helper import download_hugging_face_embeddings
-from langchain_pinecone import PineconeVectorStore
-from langchain.prompts import PromptTemplate
-from langchain_community.llms import CTransformers
-from langchain.chains import RetrievalQA
-from dotenv import load_dotenv
-from src.prompt import prompt_template
-import os
-
-load_dotenv()
-
-PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
-PINECONE_API_ENV = os.environ.get("PINECONE_API_ENV")
-
-
-embeddings = download_hugging_face_embeddings()
-index_name = "llm-chatbot"
-
-# Initializing the Pinecone
-docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)
-
-
-PROMPT = PromptTemplate(
-    template=prompt_template, input_variables=["context", "question"]
-)
-
-chain_type_kwargs = {"prompt": PROMPT}
-
-current_dir = os.getcwd()
-
-def load_llm():
-    llm = CTransformers(
-        model="TheBloke/Llama-2-7B-Chat-GGML",
-        model_type="llama",
-        max_new_tokens=512,
-        temperature=0.5
-    )
-    return llm
-    
-llm = load_llm()
-
-qa = RetrievalQA.from_chain_type(
-    llm=llm,
-    chain_type="stuff",
-    retriever=docsearch.as_retriever(search_kwargs={"k": 2}),
-    return_source_documents=True,
-    chain_type_kwargs=chain_type_kwargs,
-    verbose=True,
-)
-
-
-def llama_call(input):
-    result = qa.invoke({"query": input})
-    return str(result["result"])
-
-
-if __name__ == "__main__":
-    msg = "If a previous owner of a land had allowed a neighbour or neighbour to walk or drive over his land in a shortcut and this has been going on for say a decade or so can I as the new owner stop them now from using the shortcut?"
-    print(f"response: {llama_call(msg)}")

src/openai_call.py

@@ -1,50 +0,0 @@
-from src.helper import download_hugging_face_embeddings
-from langchain_pinecone import PineconeVectorStore
-from langchain.prompts import PromptTemplate
-from langchain_openai import OpenAI
-from langchain.chains import RetrievalQA
-from dotenv import load_dotenv
-from src.prompt import prompt_template
-import os
-
-load_dotenv()
-
-PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
-PINECONE_API_ENV = os.environ.get("PINECONE_API_ENV")
-
-
-embeddings = download_hugging_face_embeddings()
-index_name = "llm-chatbot"
-
-# Initializing the Pinecone
-docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)
-
-
-PROMPT = PromptTemplate(
-    template=prompt_template, input_variables=["context", "question"]
-)
-
-chain_type_kwargs = {"prompt": PROMPT}
-
-current_dir = os.getcwd()
-llm = OpenAI()
-
-
-qa = RetrievalQA.from_chain_type(
-    llm=llm,
-    chain_type="stuff",
-    retriever=docsearch.as_retriever(search_kwargs={"k": 2}),
-    return_source_documents=True,
-    chain_type_kwargs=chain_type_kwargs,
-    verbose=True,
-)
-
-
-def openai_call(input):
-    result = qa.invoke({"query": input})
-    return str(result["result"])
-
-
-if __name__ == "__main__":
-    msg = "If a previous owner of a land had allowed a neighbour or neighbour to walk or drive over his land in a shortcut and this has been going on for say a decade or so can I as the new owner stop them now from using the shortcut?"
-    print(f"response: {openai_call(msg)}")

src/prompt.py

@@ -1,16 +0,0 @@
-prompt_template = """
-As a seasoned legal advisor, you possess deep knowledge of legal intricacies and are skilled in referencing relevant laws and regulations. Users will seek guidance on various legal matters.
-
-If a question falls outside the scope of legal expertise, kindly inform the user that your specialization is limited to legal advice.
-
-In cases where you're uncertain of the answer, it's important to uphold integrity by admitting 'I don't know' rather than providing potentially erroneous information.
-
-Below is a snippet of context from the relevant section of the constitution, although it will not be disclosed to users.
-
-Context: {context}
-Question: {question}
-
-Your response should consist solely of helpful advice without any extraneous details.
-
-Helpful advice:
-"""