Create app.py

app.py

@@ -0,0 +1,71 @@
+import streamlit as st
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+from langchain.chat_models import ChatOpenAI
+import os
+
+# Set up OpenAI API key
+OPENAI_API_KEY = "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"
+os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
+
+def train_model_with_transcript(transcript):
+    """Train a language model using the transcript."""
+    # Split transcript into smaller chunks
+    splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    docs = splitter.split_text(transcript)
+    
+    # Create embeddings and vector store
+    embeddings = OpenAIEmbeddings()
+    vectorstore = FAISS.from_texts(docs, embeddings)
+    return vectorstore
+
+def generate_similar_content(query, vectorstore):
+    """Generate content similar to the input query using the trained model."""
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo")
+    retriever = vectorstore.as_retriever()
+    prompt_template = """
+    Use the context below to generate content similar to the provided input:
+
+    Context: {context}
+    Input Query: {query}
+
+    Similar Content:
+    """
+    prompt = PromptTemplate(input_variables=["context", "query"], template=prompt_template)
+    chain = LLMChain(llm=llm, prompt=prompt)
+    
+    context = retriever.get_relevant_documents(query)
+    context_text = " ".join([doc.page_content for doc in context])
+    
+    result = chain.run({"context": context_text, "query": query})
+    return result
+
+# Streamlit app UI
+st.title("Text-based Content Generator")
+st.markdown("Upload a transcription file, train the model, and generate similar content.")
+
+uploaded_file = st.file_uploader("Upload Transcription File (TXT):", type=["txt"])
+
+if uploaded_file:
+    with st.spinner("Reading transcription file..."):
+        transcription = uploaded_file.read().decode("utf-8")
+        st.success("Transcription file loaded successfully!")
+
+        if st.button("Train Model"):
+            with st.spinner("Training model..."):
+                vectorstore = train_model_with_transcript(transcription)
+                st.success("Model trained successfully!")
+
+query = st.text_input("Enter your query to generate similar content:")
+
+if st.button("Generate Content"):
+    if 'vectorstore' in locals():
+        with st.spinner("Generating content..."):
+            result = generate_similar_content(query, vectorstore)
+            st.success("Content generated successfully!")
+            st.text_area("Generated Content", value=result, height=200)
+    else:
+        st.error("Please train the model first by uploading a transcription file.")