Delete app.py

app.py

@@ -1,92 +0,0 @@
-import os
-import gradio as gr
-from dotenv import load_dotenv
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_community.llms import HuggingFaceHub
-from langchain_core.documents import Document
-from langchain.prompts import PromptTemplate
-from langchain.chains import LLMChain
-from langchain_community.tools.tavily_search.tool import TavilySearchResults
-
-# Load environment variables
-load_dotenv()
-HUGGINGFACEHUB_API_TOKEN = os.getenv("HF_TOKEN")
-TAVILY_API_KEY = os.getenv("TAVILY_API_KEY")
-
-# Set API keys
-os.environ["HUGGINGFACEHUB_API_TOKEN"] = HUGGINGFACEHUB_API_TOKEN
-os.environ["TAVILY_API_KEY"] = TAVILY_API_KEY
-
-# Prompt Template
-prompt_template = PromptTemplate(
-    input_variables=["context", "user_story"],
-    template="""You are a QA expert. Based on the context below and the given user story, write a detailed list of test cases.
-
-Context:
-{context}
-
-User Story:
-{user_story}
-
-Test Cases:"""
-)
-
-# Load knowledge from RAG (local file)
-def load_rag_knowledge():
-    with open("rag_knowledge_base.txt", "r", encoding="utf-8") as file:
-        content = file.read()
-    docs = [Document(page_content=content)]
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vector_store = FAISS.from_documents(docs, embeddings)
-    return vector_store.similarity_search("test case generation", k=1)
-
-# Tavily search
-def tavily_search(query):
-    search = TavilySearchResults(k=1)
-    results = search.run(query)
-    return results[0]['content'] if results else "No relevant results from Tavily."
-
-# LLM call with combined context
-def call_llm_with_context(context, user_story):
-    llm = HuggingFaceHub(
-        repo_id="mistralai/Mistral-7B-Instruct-v0.3",
-        model_kwargs={"temperature": 0.7, "max_new_tokens": 500}
-    )
-    chain = LLMChain(llm=llm, prompt=prompt_template)
-    return chain.run({"context": context, "user_story": user_story})
-
-# Generate test cases pipeline
-def generate_test_cases(user_story):
-    rag_docs = load_rag_knowledge()
-    rag_text = "\n".join([doc.page_content for doc in rag_docs])
-    tavily_text = tavily_search(user_story)
-    full_context = f"{rag_text}\n\n{tavily_text}"
-    test_cases = call_llm_with_context(full_context, user_story)
-    return rag_text.strip(), tavily_text.strip(), test_cases.strip()
-
-# Gradio handler
-def handle_generate(user_story):
-    rag, tavily, result = generate_test_cases(user_story)
-    return rag, tavily, result
-
-# ----------------- Gradio UI -----------------
-with gr.Blocks() as demo:
-    gr.Markdown("# 🧪 TechTales TestCaseGenerator using RAG + Tavily + Mistral + LangChain -  Developed by Pankaj Kumar")
-    gr.Markdown("🚀 Enter a user story below to generate test cases using your knowledge base and Tavily search.")
-
-    user_input = gr.Textbox(label="📝 Enter User Story", lines=4, placeholder="As a user, I want to...")
-
-    btn = gr.Button("🔍 Generate Test Cases")
-
-    rag_output = gr.Textbox(label="📚 Knowledge from RAG File", lines=8)
-    tavily_output = gr.Textbox(label="🌐 Knowledge from Tavily Search", lines=8)
-    result_output = gr.Textbox(label="✅ Final Test Cases", lines=12)
-
-    btn.click(
-        handle_generate,
-        inputs=[user_input],
-        outputs=[rag_output, tavily_output, result_output]
-    )
-
-demo.launch()