Delete rough.py

rough.py

@@ -1,156 +0,0 @@
-import streamlit as st
-import os
-import requests
-import chromadb
-from langchain.document_loaders import PDFPlumberLoader
-from langchain_huggingface import HuggingFaceEmbeddings
-from langchain_experimental.text_splitter import SemanticChunker
-from langchain_chroma import Chroma
-from langchain.chains import LLMChain, SequentialChain
-from langchain.prompts import PromptTemplate
-from langchain_groq import ChatGroq
-from prompts import rag_prompt, relevancy_prompt, relevant_context_picker_prompt, response_synth
-
-# ----------------- Streamlit UI Setup -----------------
-st.set_page_config(page_title="Blah", layout="wide")
-st.title("Blah-1")
-
-# ----------------- API Keys -----------------
-os.environ["GROQ_API_KEY"] = st.secrets.get("GROQ_API_KEY", "")
-
-# ----------------- Ensure Vector Store Directory Exists -----------------
-if not os.path.exists("./chroma_langchain_db"):
-    os.makedirs("./chroma_langchain_db")
-
-# ----------------- Clear ChromaDB Cache -----------------
-chromadb.api.client.SharedSystemClient.clear_system_cache()
-
-# ----------------- Initialize Session State -----------------
-if "pdf_loaded" not in st.session_state:
-    st.session_state.pdf_loaded = False
-if "chunked" not in st.session_state:
-    st.session_state.chunked = False
-if "vector_created" not in st.session_state:
-    st.session_state.vector_created = False
-if "processed_chunks" not in st.session_state:
-    st.session_state.processed_chunks = None
-if "vector_store" not in st.session_state:
-    st.session_state.vector_store = None
-
-# ----------------- Load Models -------------------
-llm_judge = ChatGroq(model="deepseek-r1-distill-llama-70b")
-rag_llm = ChatGroq(model="mixtral-8x7b-32768")
-
-# Enable verbose logging for debugging
-llm_judge.verbose = True
-rag_llm.verbose = True
-
-# ----------------- PDF Selection (Upload or URL) -----------------
-st.sidebar.subheader("📂 PDF Selection")
-pdf_source = st.radio("Choose a PDF source:", ["Upload a PDF file", "Enter a PDF URL"], index=0, horizontal=True)
-
-if pdf_source == "Upload a PDF file":
-    uploaded_file = st.sidebar.file_uploader("Upload your PDF file", type=["pdf"])
-    if uploaded_file:
-        st.session_state.pdf_path = "temp.pdf"
-        with open(st.session_state.pdf_path, "wb") as f:
-            f.write(uploaded_file.getbuffer())
-        st.session_state.pdf_loaded = False
-        st.session_state.chunked = False
-        st.session_state.vector_created = False
-
-elif pdf_source == "Enter a PDF URL":
-    pdf_url = st.sidebar.text_input("Enter PDF URL:")
-    if pdf_url and not st.session_state.pdf_loaded:
-        with st.spinner("🔄 Downloading PDF..."):
-            try:
-                response = requests.get(pdf_url)
-                if response.status_code == 200:
-                    st.session_state.pdf_path = "temp.pdf"
-                    with open(st.session_state.pdf_path, "wb") as f:
-                        f.write(response.content)
-                    st.session_state.pdf_loaded = False
-                    st.session_state.chunked = False
-                    st.session_state.vector_created = False
-                    st.success("✅ PDF Downloaded Successfully!")
-                else:
-                    st.error("❌ Failed to download PDF. Check the URL.")
-            except Exception as e:
-                st.error(f"Error downloading PDF: {e}")
-
-# ----------------- Process PDF -----------------
-if not st.session_state.pdf_loaded and "pdf_path" in st.session_state:
-    with st.spinner("🔄 Processing document... Please wait."):
-        loader = PDFPlumberLoader(st.session_state.pdf_path)
-        docs = loader.load()
-
-        # Embedding Model (HF on CPU)
-        model_name = "nomic-ai/modernbert-embed-base"
-        embedding_model = HuggingFaceEmbeddings(model_name=model_name, model_kwargs={"device": "cpu"})
-
-        # Split into Chunks
-        text_splitter = SemanticChunker(embedding_model)
-        document_chunks = text_splitter.split_documents(docs)
-
-        # Store chunks in session state
-        st.session_state.processed_chunks = document_chunks
-        st.session_state.pdf_loaded = True
-        st.success("✅ Document processed and chunked successfully!")
-
-# ----------------- Setup Vector Store  -----------------
-if not st.session_state.vector_created and st.session_state.processed_chunks:
-    with st.spinner("🔄 Initializing Vector Store..."):
-        vector_store = Chroma(
-            collection_name="deepseek_collection",
-            collection_metadata={"hnsw:space": "cosine"},
-            embedding_function=embedding_model,
-            persist_directory="./chroma_langchain_db"
-        )
-        vector_store.add_documents(st.session_state.processed_chunks)
-        st.session_state.vector_store = vector_store
-        st.session_state.vector_created = True
-        st.success("✅ Vector store initialized successfully!")
-
-# ----------------- Query Input -----------------
-query = st.text_input("🔍 Ask a question about the document:")
-
-if query:
-    with st.spinner("🔄 Retrieving relevant context..."):
-        retriever = st.session_state.vector_store.as_retriever(search_type="similarity", search_kwargs={"k": 5})
-        retrieved_docs = retriever.invoke(query)
-        context = [d.page_content for d in retrieved_docs]
-        st.success("✅ Context retrieved successfully!")
-
-    # ----------------- Full SequentialChain Execution -----------------
-    with st.spinner("🔄 Running full pipeline..."):
-        context_relevancy_checker_prompt = PromptTemplate(input_variables=["retriever_query", "context"], template=relevancy_prompt)
-        relevant_prompt = PromptTemplate(input_variables=["relevancy_response"], template=relevant_context_picker_prompt)
-        context_prompt = PromptTemplate(input_variables=["context_number", "context"], template=response_synth)
-        final_prompt = PromptTemplate(input_variables=["query", "context"], template=rag_prompt)
-
-        context_relevancy_chain = LLMChain(llm=llm_judge, prompt=context_relevancy_checker_prompt, output_key="relevancy_response")
-        relevant_context_chain = LLMChain(llm=llm_judge, prompt=relevant_prompt, output_key="context_number")
-        relevant_contexts_chain = LLMChain(llm=llm_judge, prompt=context_prompt, output_key="relevant_contexts")
-        response_chain = LLMChain(llm=rag_llm, prompt=final_prompt, output_key="final_response")
-
-        context_management_chain = SequentialChain(
-            chains=[context_relevancy_chain, relevant_context_chain, relevant_contexts_chain, response_chain],
-            input_variables=["context", "retriever_query", "query"],
-            output_variables=["relevancy_response", "context_number", "relevant_contexts", "final_response"]
-        )
-
-        final_output = context_management_chain.invoke({"context": context, "retriever_query": query, "query": query})
-        st.success("✅ Full pipeline executed successfully!")
-
-    # ----------------- Display All Outputs (Formatted) -----------------
-    st.markdown("### 🟥 Context Relevancy Evaluation")
-    st.json(final_output["relevancy_response"])
-
-    st.markdown("### 🟦 Picked Relevant Contexts")
-    st.json(final_output["context_number"])
-
-    st.markdown("### 🟥 Extracted Relevant Contexts")
-    st.json(final_output["relevant_contexts"])
-
-    st.markdown("## 🟥 RAG Final Response")
-    st.write(final_output["final_response"])