updated ui2

loader.py

@@ -0,0 +1,10 @@
+# loader.py
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+def load_and_split_pdf(pdf_path):
+    loader = PyPDFLoader(pdf_path)
+    docs = loader.load()
+
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    return splitter.split_documents(docs)

rag_chain.py

@@ -0,0 +1,20 @@
+# rag_chain.py
+from langchain.vectorstores import Chroma
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from langchain.llms import HuggingFaceHub
+
+def setup_rag_chain(docs):
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    vectorstore = Chroma.from_documents(docs, embedding=embeddings)
+
+    retriever = vectorstore.as_retriever()
+    
+    # Replace this with your own hosted LLaMA 3.1 if needed
+    llm = HuggingFaceHub(
+        repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
+        model_kwargs={"temperature": 0.3, "max_tokens": 512}
+    )
+
+    qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
+    return qa_chain

tts.py

@@ -1,8 +0,0 @@
-from TTS.api import TTS
-
-
-tts = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)
-
-def generate_speech(text, filename="output.wav"):
-    tts.tts_to_file(text=text, file_path=filename)
-    return filename

tts_engine.py

@@ -0,0 +1,7 @@
+from TTS.api import TTS
+
+tts = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", gpu=False)
+
+def generate_voice(text, path="podcast.wav"):
+    tts.tts_to_file(text=text, file_path=path)
+    return path