initial no content

.gitignore

@@ -0,0 +1,16 @@
+.env
+*.key
+*.pem
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+.vscode/
+*.code-workspace
+.DS_Store
+Thumbs.db
+*.log
+*.tmp
+faiss_index/
+*.faiss

app.py

@@ -0,0 +1,110 @@
+import os
+from dotenv import load_dotenv
+from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFDirectoryLoader, WebBaseLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain.tools.retriever import create_retriever_tool
+from langchain.agents import create_tool_calling_agent, AgentExecutor
+from langchain_core.tools import tool
+import gradio as gr
+import numpy as np
+
+load_dotenv()
+os.environ['USER_AGENT'] = os.getenv('USER_AGENT', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)')
+
+def load_web_resources(file='websites.txt'):
+    urls = ['https://steveblank.com/']
+    if os.path.exists(file):
+        with open(file, 'r') as f:
+            urls.extend(line.strip() for line in f if line.strip())
+    web_docs = []
+    for url in urls:
+        try:
+            loader = WebBaseLoader(url)
+            web_docs.extend(loader.load())
+        except Exception as e:
+            print(f"Failed to load {url}: {e}")
+    return web_docs
+
+def build_vectorstore(pdf_dir="ConvertedFiles"):
+    loader = PyPDFDirectoryLoader(pdf_dir)
+    docs = loader.load()
+    web_docs = load_web_resources()
+    all_docs = docs + web_docs
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    splits = splitter.split_documents(all_docs)
+    embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+    vectorstore = FAISS.from_documents(splits, embeddings)
+    vectorstore.save_local("faiss_index")
+    return vectorstore
+
+@tool
+def scenario_simulator(params: dict) -> str:
+    """Simulates product adoption using Monte Carlo. Params: initial_users, growth_rate, time_months, uncertainty."""
+    try:
+        initial_users = params.get("initial_users", 1000)
+        growth_rate = params.get("growth_rate", 0.05)  # 5%/month
+        time_months = params.get("time_months", 12)
+        uncertainty = params.get("uncertainty", 0.1)  # 10% variance
+        runs = 1000
+        final_users = []
+        for _ in range(runs):
+            users = initial_users
+            for _ in range(time_months):
+                users *= (1 + np.random.normal(growth_rate, uncertainty))
+            final_users.append(users)
+        mean = np.mean(final_users)
+        std = np.std(final_users)
+        return f"Predicted users after {time_months} months: {mean:.0f} ± {std:.0f} (mean ± std, {runs} runs)."
+    except Exception as e:
+        return f"Sim error: {e}. Check params: {params}"
+
+def setup_agent(vectorstore):
+    retriever_tool = create_retriever_tool(
+        vectorstore.as_retriever(search_kwargs={"k": 5}),
+        "course_materials_retriever",
+        "Searches PDFs and crawled web resources on optimization/sim/decision tech/project mgmt/lean startup."
+    )
+    web_tool = TavilySearchResults(max_results=3)
+    tools = [retriever_tool, web_tool, scenario_simulator]
+    llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.3)
+    prompt = ChatPromptTemplate.from_messages([
+        ("system", "You are Dr. Sue Cohen's Teaching Assistant, a passionate tutor for Applied Optimization/Simulation/Decision Tech/Project Mgmt. Guide users with sharp insights, probing questions, and hints from course materials/web. Be witty (e.g., 'Solid, but don’t optimize for chaos—how’s this tie to diffusion?'), professional, encouraging. Run scenario sims for adoption/scalability queries with clear params. Prioritize course/web data, use web for updates. Be concise, cite sources, never solve outright, redirect if off-topic, prompt next steps."),
+        ("human", "{input}"),
+        MessagesPlaceholder("agent_scratchpad")
+    ])
+    agent = create_tool_calling_agent(llm, tools, prompt)
+    executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+    return executor
+
+def chat(message, history):
+    # Parse query for scenario_simulator if needed
+    if "initial_users" in message:
+        params = {}
+        for pair in message.split(","):
+            key, value = pair.split(":")
+            key = key.strip()
+            value = float(value.strip().replace("%", "")) / 100 if "%" in value else int(value.strip())
+            params[key] = value
+        return scenario_simulator(params)
+    return agent.invoke({"input": message})["output"]
+
+if not os.path.exists("faiss_index"):
+    vectorstore = build_vectorstore()
+else:
+    embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+    vectorstore = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+
+agent = setup_agent(vectorstore)
+
+demo = gr.ChatInterface(
+    fn=chat,
+    title="Opt/Sim Project RAG Bot",
+    description="Query materials + web aug, e.g., 'Latest on genetic algos in scheduling?'"
+)
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)

file_convert.py

@@ -0,0 +1,52 @@
+import os
+import shutil
+import sys
+
+# For .docx conversion
+try:
+    from docx2pdf import convert as docx_convert
+except ImportError:
+    print("Error: docx2pdf not installed. Run 'pip install docx2pdf' and try again.")
+    sys.exit(1)
+
+# For .pptx conversion (requires PowerPoint installed)
+try:
+    import win32com.client
+except ImportError:
+    print("Error: pywin32 not installed. Run 'pip install pywin32' and try again.")
+    sys.exit(1)
+
+def main(input_dir, output_dir):
+    if not os.path.isdir(input_dir):
+        print(f"Error: {input_dir} is not a directory.")
+        sys.exit(1)
+    
+    os.makedirs(output_dir, exist_ok=True)
+    
+    for root, dirs, files in os.walk(input_dir):
+        rel_dir = os.path.relpath(root, input_dir)
+        target_subdir = os.path.join(output_dir, rel_dir)
+        os.makedirs(target_subdir, exist_ok=True)
+        
+        for file in files:
+            filepath = os.path.join(root, file)
+            base, ext = os.path.splitext(file)
+            output_pdf = os.path.join(target_subdir, base + '.pdf')
+            
+            if ext.lower() == '.docx':
+                docx_convert(filepath, output_pdf)
+            elif ext.lower() == '.pptx':
+                try:
+                    ppt_app = win32com.client.Dispatch("PowerPoint.Application")
+                    pres = ppt_app.Presentations.Open(os.path.abspath(filepath), WithWindow=False)
+                    pres.SaveAs(output_pdf, 32)  # 32 = ppSaveAsPDF
+                    pres.Close()
+                    ppt_app.Quit()
+                except Exception as e:
+                    print(f"Failed to convert {filepath}: {e}. PowerPoint installed?")
+            elif ext.lower() == '.pdf':
+                shutil.copy(filepath, output_pdf)
+
+
+
+main("OrigFolder","ConvertedFiles")

pythia.py

@@ -0,0 +1,23 @@
+import numpy as np
+from langchain_core.tools import tool
+
+@tool
+def scenario_simulator(query: str, params: dict) -> str:
+    """Simulates product adoption scenarios using Monte Carlo. Params: initial_users, growth_rate, time_months, uncertainty."""
+    try:
+        initial_users = params.get("initial_users", 1000)
+        growth_rate = params.get("growth_rate", 0.05)  # 5%/month default
+        time_months = params.get("time_months", 12)
+        uncertainty = params.get("uncertainty", 0.1)  # 10% variance
+        runs = 1000
+        final_users = []
+        for _ in range(runs):
+            users = initial_users
+            for _ in range(time_months):
+                users *= (1 + np.random.normal(growth_rate, uncertainty))
+            final_users.append(users)
+        mean = np.mean(final_users)
+        std = np.std(final_users)
+        return f"Predicted users after {time_months} months: {mean:.0f} ± {std:.0f} (mean ± std, {runs} runs)."
+    except Exception as e:
+        return f"Sim error: {e}. Check params: {params}"