Rename pages/jarvis.py to pages/descriptionGen.py

pages/descriptionGen.py

@@ -0,0 +1,50 @@
+import streamlit as st
+from langchain.prompts import PromptTemplate
+from langchain.chat_models import ChatOpenAI
+from langchain.base_language import BaseLanguageModel
+from langchain.chains.llm import LLMChain
+import openai
+import os
+
+# Set up the API key (you can also use st.secrets for security)
+OPENAI_API_KEY = st.text_input("OPENAI_API_KEY", type="password")
+
+prompt_file = "prompt_template.txt"
+
+class ProductDescGen(LLMChain):
+    """LLM Chain specifically for generating multi-paragraph rich text product description using emojis."""
+
+    @classmethod
+    def from_llm(cls, llm: BaseLanguageModel, prompt: str, **kwargs: Any) -> ProductDescGen:
+        """Load ProductDescGen Chain from LLM."""
+        return cls(llm=llm, prompt=prompt, **kwargs)
+
+def product_desc_generator(product_name, keywords, api_key):
+    with open(prompt_file, "r") as file:
+        prompt_template = file.read()
+
+    PROMPT = PromptTemplate(input_variables=["product_name", "keywords"], template=prompt_template)
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.7, openai_api_key=api_key)
+
+    ProductDescGen_chain = ProductDescGen.from_llm(llm=llm, prompt=PROMPT)
+    ProductDescGen_query = ProductDescGen_chain.apply_and_parse([{"product_name": product_name, "keywords": keywords}])
+    return ProductDescGen_query[0]["text"]
+
+st.title("Product Description Generator")
+
+st.write(
+    "Generate multi-paragraph rich text product descriptions for your products instantly!"
+    " Provide the product name and keywords related to the product."
+)
+
+product_name = st.text_input("Product Name", "Nike Shoes")
+keywords = st.text_input("Keywords (separated by commas)", "black shoes, leather shoes for men, water resistant")
+
+if st.button("Generate Description"):
+    if OPENAI_API_KEY:
+        description = product_desc_generator(product_name, keywords, OPENAI_API_KEY)
+        st.subheader("Product Description:")
+        st.text(description)
+    else:
+        st.warning("Please provide your OpenAI API Key.")
+

pages/jarvis.py

@@ -1,106 +0,0 @@
-import streamlit as st
-import os
-from pathlib import Path
-from langchain_community.document_loaders import PyPDFLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.vectorstores import Chroma
-from langchain.chains import ConversationalRetrievalChain
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.llms import HuggingFaceEndpoint
-from langchain.memory import ConversationBufferMemory
-from unidecode import unidecode
-import chromadb
-import re
-
-list_llm = [
-    "mistralai/Mistral-7B-Instruct-v0.2", "mistralai/Mixtral-8x7B-Instruct-v0.1", 
-    "mistralai/Mistral-7B-Instruct-v0.1", "google/gemma-7b-it", "google/gemma-2b-it", 
-    "HuggingFaceH4/zephyr-7b-beta", "HuggingFaceH4/zephyr-7b-gemma-v0.1", 
-    "meta-llama/Llama-2-7b-chat-hf", "microsoft/phi-2", 
-    "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "mosaicml/mpt-7b-instruct", "tiiuae/falcon-7b-instruct", 
-    "google/flan-t5-xxl"
-]
-
-def load_doc(list_file_path, chunk_size, chunk_overlap):
-    loaders = [PyPDFLoader(x) for x in list_file_path]
-    pages = []
-    for loader in loaders:
-        pages.extend(loader.load())
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
-    doc_splits = text_splitter.split_documents(pages)
-    return doc_splits
-
-def create_db(splits, collection_name):
-    embedding = HuggingFaceEmbeddings()
-    new_client = chromadb.EphemeralClient()
-    vectordb = Chroma.from_documents(
-        documents=splits,
-        embedding=embedding,
-        client=new_client,
-        collection_name=collection_name
-    )
-    return vectordb
-
-def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db):
-    llm = HuggingFaceEndpoint(repo_id=llm_model, temperature=temperature, max_new_tokens=max_tokens, top_k=top_k)
-    memory = ConversationBufferMemory(memory_key="chat_history", output_key='answer', return_messages=True)
-    retriever = vector_db.as_retriever()
-    qa_chain = ConversationalRetrievalChain.from_llm(
-        llm,
-        retriever=retriever,
-        chain_type="stuff",
-        memory=memory,
-        return_source_documents=True,
-        verbose=False
-    )
-    return qa_chain
-
-def create_collection_name(file_path):
-    collection_name = Path(file_path).stem
-    collection_name = unidecode(collection_name)
-    collection_name = re.sub('[^A-Za-z0-9]+', '-', collection_name)
-    collection_name = collection_name[:50]
-    if len(collection_name) < 3:
-        collection_name = collection_name + 'xyz'
-    if not collection_name[0].isalnum():
-        collection_name = 'A' + collection_name[1:]
-    if not collection_name[-1].isalnum():
-        collection_name = collection_name[:-1] + 'Z'
-    return collection_name
-
-def main():
-    st.title("PDF-based Chatbot")
-
-    uploaded_files = st.file_uploader("Upload PDF documents (single or multiple)", type="pdf", accept_multiple_files=True)
-
-    if uploaded_files:
-        chunk_size = st.slider("Chunk size", min_value=100, max_value=1000, value=600, step=20)
-        chunk_overlap = st.slider("Chunk overlap", min_value=10, max_value=200, value=40, step=10)
-
-        list_file_path = [file.name for file in uploaded_files]
-
-        if st.button("Generate Vector Database"):
-            st.text("Loading documents...")
-            doc_splits = load_doc(list_file_path, chunk_size, chunk_overlap)
-            st.text("Creating vector database...")
-            collection_name = create_collection_name(list_file_path[0])
-            vector_db = create_db(doc_splits, collection_name)
-
-            llm_model = st.selectbox("Choose LLM Model", list_llm)
-            temperature = st.slider("Temperature", min_value=0.01, max_value=1.0, value=0.7, step=0.1)
-            max_tokens = st.slider("Max Tokens", min_value=224, max_value=4096, value=1024, step=32)
-            top_k = st.slider("Top-K Samples", min_value=1, max_value=10, value=3, step=1)
-
-            if st.button("Initialize QA Chain"):
-                st.text("Initializing QA chain...")
-                qa_chain = initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db)
-
-                st.header("Chatbot")
-                message = st.text_input("Type your message")
-                if st.button("Submit"):
-                    st.text("Generating response...")
-                    response = qa_chain({"question": message, "chat_history": []})
-                    st.write("Assistant:", response["answer"])
-
-if __name__ == "__main__":
-    main()