Initial commit: RAGGER - Sistema RAG per associazione di volontariato

app.py

@@ -0,0 +1,400 @@
+import streamlit as st
+from pathlib import Path
+import time
+
+from config import settings
+from core import rag
+from agent import agent, AgentMode
+from ollama_client import ollama, LLMClient, PROVIDER_BASE_URLS
+from logger import get_logger
+
+log = get_logger("app")
+
+from document_processor import DocumentProcessor
+
+SUPPORTED_EXTENSIONS = list(DocumentProcessor.SUPPORTED_EXTENSIONS.keys())
+
+PROVIDER_MODELS = {
+    "ollama": ["gemma2:9b", "llama3.2", "llama3.1", "mistral"],
+    "opencode": ["claude-3.5-sonnet", "gpt-4o", "gemini-2.0-flash", "deepseek-r1", "llama-3.3-70b"],
+    "openrouter": ["openrouter/auto", "anthropic/claude-3.5-sonnet", "google/gemini-pro-1.5", "meta-llama/llama-3.1-70b-instruct"],
+    "groq": ["llama-3.1-70b-versatile", "llama-3.1-8b-instant", "mixtral-8x7b-32768"],
+    "openai": ["gpt-4o", "gpt-4o-mini", "gpt-4-turbo"]
+}
+
+st.set_page_config(
+    page_title="RAGGER",
+    page_icon="📚",
+    layout="wide"
+)
+
+
+def save_settings(provider, model, api_key, base_url, ollama_host, ollama_model):
+    env_path = Path(".env")
+    lines = []
+    
+    if env_path.exists():
+        for line in env_path.read_text().splitlines():
+            if line.startswith("LLM_PROVIDER="):
+                lines.append(f"LLM_PROVIDER={provider}")
+            elif line.startswith("LLM_MODEL="):
+                lines.append(f"LLM_MODEL={model}")
+            elif line.startswith("LLM_API_KEY="):
+                lines.append(f"LLM_API_KEY={api_key}")
+            elif line.startswith("LLM_BASE_URL="):
+                lines.append(f"LLM_BASE_URL={base_url}")
+            elif line.startswith("OLLAMA_HOST="):
+                lines.append(f"OLLAMA_HOST={ollama_host}")
+            elif line.startswith("OLLAMA_MODEL="):
+                lines.append(f"OLLAMA_MODEL={ollama_model}")
+            else:
+                lines.append(line)
+    else:
+        lines = [
+            f"LLM_PROVIDER={provider}",
+            f"LLM_MODEL={model}",
+            f"LLM_API_KEY={api_key}",
+            f"LLM_BASE_URL={base_url}",
+            f"OLLAMA_HOST={ollama_host}",
+            f"OLLAMA_MODEL={ollama_model}",
+        ]
+    
+    env_path.write_text("\n".join(lines) + "\n")
+    log.info(f"Settings saved: provider={provider}, model={model}")
+
+
+def check_health():
+    log.debug("Running startup health check")
+    issues = []
+    
+    if not ollama.is_available():
+        issues.append("Ollama non raggiungibile")
+        log.warning("Ollama not available at startup")
+    
+    return issues
+
+
+startup_issues = check_health()
+if startup_issues:
+    st.warning("⚠️ Problemi rilevati: " + ", ".join(startup_issues))
+
+
+def show_logs():
+    """Mostra i log dell'applicazione"""
+    log_file = Path("logs/ragger.log")
+    if log_file.exists():
+        lines = log_file.read_text().splitlines()
+        last_lines = lines[-50:] if len(lines) > 50 else lines
+        return "\n".join(last_lines)
+    return "Nessun log disponibile"
+
+
+def check_ollama_status():
+    """Verifica se Ollama sta elaborando qualcosa"""
+    try:
+        import httpx
+        resp = httpx.get(f"{settings.OLLAMA_HOST}/api/tags", timeout=5)
+        return resp.status_code == 200
+    except:
+        return False
+
+
+st.title("📚 RAGGER")
+st.caption("Sistema RAG con Agent Intelligente")
+
+
+with st.sidebar:
+    st.header("⚙️ Modalità")
+    
+    mode = st.selectbox(
+        "Seleziona modalità",
+        options=["chat", "lettera", "progetto", "impostazioni"],
+        index=0,
+        format_func=lambda x: {
+            "chat": "💬 Chat",
+            "lettera": "✉️ Lettera",
+            "progetto": "📋 Progetto",
+            "impostazioni": "⚙️ Impostazioni"
+        }[x]
+    )
+    
+    st.divider()
+    
+    with st.expander("📜 Log Applicazione", expanded=True):
+        log_content = show_logs()
+        st.text_area("", log_content, height=200, key="log_viewer", disabled=True)
+        
+        col_log1, col_log2 = st.columns(2)
+        with col_log1:
+            if st.button("🔄 Aggiorna Log", use_container_width=True):
+                st.rerun()
+        with col_log2:
+            if st.button("📋 Copia Log", use_container_width=True):
+                st.write("Log copiato!")
+    
+    ollama_status = check_ollama_status()
+    if ollama_status:
+        st.success("🟢 Ollama connesso")
+    else:
+        st.error("🔴 Ollama non risponde")
+    
+    if mode == "impostazioni":
+        st.divider()
+        st.header("Configurazione")
+        st.write(f"**Ollama:** {settings.OLLAMA_HOST}")
+        st.write(f"**Modello:** {settings.OLLAMA_MODEL}")
+        st.write(f"**Embedding:** {settings.OLLAMA_EMBED_MODEL}")
+        
+        if st.button("Test Connessione Ollama"):
+            with st.spinner("Testing..."):
+                if ollama.is_available():
+                    st.success("✅ Ollama connesso!")
+                else:
+                    st.error("❌ Ollama non raggiungibile")
+        
+        stats = rag.get_stats()
+        st.metric("Documenti indicizzati", stats["total_chunks"])
+        
+        st.divider()
+        
+        tab_imp, _ = st.tabs(["⚙️ Impostazioni"])
+        with tab_imp:
+            st.header("⚙️ Impostazioni Provider LLM")
+            
+            current_provider = settings.LLM_PROVIDER
+            all_providers = ["ollama", "opencode", "openrouter", "groq", "openai"]
+            provider = st.selectbox(
+                "Provider",
+                options=all_providers,
+                index=all_providers.index(current_provider) if current_provider in all_providers else 0
+            )
+            
+            if provider == "ollama":
+                st.info("🏠 **Ollama** - Locale/On-premise")
+                ollama_host = st.text_input("Ollama Host", value=settings.OLLAMA_HOST)
+                ollama_models = ollama.list_models() or PROVIDER_MODELS["ollama"]
+                model = st.selectbox("Modello", options=ollama_models, index=0)
+                api_key = ""
+                base_url = ""
+            elif provider == "opencode":
+                st.info("🧘 **OpenCode Zen**")
+                api_key = st.text_input("API Key", value=settings.LLM_API_KEY or "", type="password")
+                base_url = st.text_input("Base URL", value=settings.LLM_BASE_URL or PROVIDER_BASE_URLS["opencode"])
+                models = PROVIDER_MODELS.get(provider, [])
+                model = st.selectbox("Modello", options=models, index=0)
+                ollama_host = settings.OLLAMA_HOST
+            else:
+                st.info(f"🌐 **{provider.capitalize()}**")
+                api_key = st.text_input("API Key", value=settings.LLM_API_KEY or "", type="password")
+                default_url = PROVIDER_BASE_URLS.get(provider, "")
+                base_url = st.text_input("Base URL", value=settings.LLM_BASE_URL or default_url)
+                models = PROVIDER_MODELS.get(provider, [])
+                model = st.selectbox("Modello", options=models, index=0)
+                ollama_host = settings.OLLAMA_HOST
+            
+            col1, col2 = st.columns(2)
+            with col1:
+                if st.button("💾 Salva", type="primary"):
+                    save_settings(provider, model, api_key, base_url, ollama_host, model if provider == "ollama" else settings.OLLAMA_MODEL)
+                    st.success("✅ Salvato!")
+            with col2:
+                if st.button("🔄 Ricarica"):
+                    st.rerun()
+            
+            st.json({
+                "provider": settings.LLM_PROVIDER,
+                "model": settings.LLM_MODEL or settings.OLLAMA_MODEL,
+            })
+
+
+if mode == "chat":
+    with st.sidebar:
+        st.divider()
+        st.header("📄 Documenti")
+        
+        uploaded = st.file_uploader(
+            "Carica documento",
+            type=SUPPORTED_EXTENSIONS,
+            accept_multiple_files=True
+        )
+        
+        if uploaded:
+            for file in uploaded:
+                if st.button(f"Indicizza: {file.name}", key=f"idx_{file.name}"):
+                    save_path = Path(settings.UPLOAD_DIR) / file.name
+                    save_path.write_bytes(file.getbuffer())
+                    
+                    with st.spinner(f"Indicizzando {file.name}..."):
+                        try:
+                            result = rag.ingest_document(save_path)
+                            st.success(f"✅ {result['chunks_created']} chunks")
+                        except Exception as e:
+                            st.error(f"❌ {e}")
+        
+        stats = rag.get_stats()
+        st.metric("Chunks indicizzati", stats["total_chunks"])
+    
+    st.header("💬 Chat con i tuoi documenti")
+    
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+    
+    for msg in st.session_state.messages:
+        with st.chat_message(msg["role"]):
+            st.write(msg["content"])
+            if "sources" in msg:
+                with st.expander("📚 Fonti"):
+                    for src in msg["sources"]:
+                        st.write(f"- **{src['source']}**" + 
+                                (f" (pag. {src['page']})" if src['page'] else ""))
+    
+    if prompt := st.chat_input("Fai una domanda..."):
+        log.info(f"Chat prompt: {prompt[:50]}...")
+        st.session_state.messages.append({"role": "user", "content": prompt})
+        
+        with st.chat_message("user"):
+            st.write(prompt)
+        
+        with st.chat_message("assistant"):
+            with st.spinner("Elaborazione in corso..."):
+                result = agent.process(prompt, mode="chat")
+            
+            st.write(result["answer"])
+            
+            if result.get("sources"):
+                with st.expander("📚 Fonti"):
+                    for src in result["sources"]:
+                        st.write(f"- **{src['source']}**" + 
+                                (f" (pag. {src['page']})" if src['page'] else "") +
+                                f" - Score: {src['score']:.2f}")
+                        st.caption(src["excerpt"])
+            
+            st.session_state.messages.append({
+                "role": "assistant",
+                "content": result["answer"],
+                "sources": result.get("sources", [])
+            })
+
+
+elif mode == "lettera":
+    with st.sidebar:
+        st.divider()
+        st.header("📄 Documenti")
+        
+        uploaded = st.file_uploader(
+            "Carica documento",
+            type=SUPPORTED_EXTENSIONS,
+            accept_multiple_files=True
+        )
+        
+        if uploaded:
+            for file in uploaded:
+                if st.button(f"Indicizza: {file.name}", key=f"idx_{file.name}"):
+                    save_path = Path(settings.UPLOAD_DIR) / file.name
+                    save_path.write_bytes(file.getbuffer())
+                    
+                    with st.spinner(f"Indicizzando {file.name}..."):
+                        try:
+                            result = rag.ingest_document(save_path)
+                            st.success(f"✅ {result['chunks_created']} chunks")
+                        except Exception as e:
+                            st.error(f"❌ {e}")
+        
+        stats = rag.get_stats()
+        st.metric("Chunks indicizzati", stats["total_chunks"])
+    
+    st.header("✉️ Genera Lettera")
+    
+    topic = st.text_area("Argomento della lettera", placeholder="Es: Richiesta di patrocinio per evento annuale...")
+    context = st.text_area("Contesto aggiuntivo (opzionale)", placeholder="Dettagli specifici, destinatario, tono...")
+    
+    col1, col2 = st.columns([1, 1])
+    with col1:
+        if st.button("✉️ Genera Lettera", type="primary", use_container_width=True):
+            if not topic:
+                st.warning("Inserisci un argomento")
+            else:
+                with st.spinner("Generazione in corso..."):
+                    result = agent.process(topic, mode="lettera", context=context)
+                
+                st.session_state["last_letter"] = result["answer"]
+    
+    with col2:
+        if st.button("🗑️ Pulisci", use_container_width=True):
+            if "last_letter" in st.session_state:
+                del st.session_state["last_letter"]
+            st.rerun()
+    
+    if "last_letter" in st.session_state:
+        st.divider()
+        st.subheader("Lettera generata")
+        st.text_area("", st.session_state["last_letter"], height=400, key="letter_output")
+        
+        c1, c2 = st.columns(2)
+        with c1:
+            st.button("📋 Copia", on_click=lambda: st.write("Copiato!"))
+        with c2:
+            st.button("💾 Salva")
+
+
+elif mode == "progetto":
+    with st.sidebar:
+        st.divider()
+        st.header("📄 Documenti")
+        
+        uploaded = st.file_uploader(
+            "Carica documento",
+            type=SUPPORTED_EXTENSIONS,
+            accept_multiple_files=True
+        )
+        
+        if uploaded:
+            for file in uploaded:
+                if st.button(f"Indicizza: {file.name}", key=f"idx_{file.name}"):
+                    save_path = Path(settings.UPLOAD_DIR) / file.name
+                    save_path.write_bytes(file.getbuffer())
+                    
+                    with st.spinner(f"Indicizzando {file.name}..."):
+                        try:
+                            result = rag.ingest_document(save_path)
+                            st.success(f"✅ {result['chunks_created']} chunks")
+                        except Exception as e:
+                            st.error(f"❌ {e}")
+        
+        stats = rag.get_stats()
+        st.metric("Chunks indicizzati", stats["total_chunks"])
+    
+    st.header("📋 Genera Proposta Progetto")
+    
+    title = st.text_input("Titolo del progetto", placeholder="Es: Insieme senza confini")
+    description = st.text_area("Descrizione", placeholder="Descrivi l'obiettivo, il target, le attività previste...")
+    
+    col1, col2 = st.columns([1, 1])
+    with col1:
+        if st.button("📋 Genera Proposta", type="primary", use_container_width=True):
+            if not title or not description:
+                st.warning("Inserisci titolo e descrizione")
+            else:
+                with st.spinner("Generazione in corso..."):
+                    result = agent.process(description, mode="progetto", context=title)
+                
+                st.session_state["last_project"] = result["answer"]
+    
+    with col2:
+        if st.button("🗑️ Pulisci", use_container_width=True):
+            if "last_project" in st.session_state:
+                del st.session_state["last_project"]
+            st.rerun()
+    
+    if "last_project" in st.session_state:
+        st.divider()
+        st.subheader("Proposta generata")
+        st.text_area("", st.session_state["last_project"], height=500, key="project_output")
+        
+        c1, c2, c3 = st.columns(3)
+        with c1:
+            st.button("📋 Copia")
+        with c2:
+            st.button("💾 Salva")
+        with c3:
+            st.button("📧 Email")