agent-framework-lib 0.8.1.post8__tar.gz → 0.8.2__tar.gz

{agent_framework_lib-0.8.1.post8/agent_framework_lib.egg-info → agent_framework_lib-0.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-framework-lib
-Version: 0.8.1.post8
+Version: 0.8.2
 Summary: A comprehensive Python framework for building and serving conversational AI agents with FastAPI
 Author-email: Sebastian Pavel <sebastian@cinco.ai>, Elliott Girard <elliott.girard@icloud.com>
 Maintainer-email: Sebastian Pavel <sebastian@cinco.ai>
@@ -89,6 +89,8 @@ Provides-Extra: excel
 Requires-Dist: openpyxl>=3.1.0; extra == "excel"
 Provides-Extra: drawio
 Requires-Dist: drawpyo>=0.1.0; extra == "drawio"
+Provides-Extra: gitnexus
+Requires-Dist: httpx>=0.27.0; extra == "gitnexus"
 Provides-Extra: dev
 Requires-Dist: pytest>=8.4.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
@@ -186,7 +188,7 @@ uv add agent-framework-lib[llamaindex,mcp]
 uv add agent-framework-lib[all]
 ```
 
-**Available extras:** `llamaindex`, `mcp`, `mongodb`, `elasticsearch`, `postgresql`, `s3`, `minio`, `gcp`, `multimodal`, `memory`, `memori`, `graphiti`, `graphiti-falkordb`, `graphiti-neo4j`, `graphiti-all`, `observability`, `monitoring`, `websearch`, `dev`, `all`
+**Available extras:** `llamaindex`, `mcp`, `gitnexus`, `mongodb`, `elasticsearch`, `postgresql`, `s3`, `minio`, `gcp`, `multimodal`, `memory`, `memori`, `graphiti`, `graphiti-falkordb`, `graphiti-neo4j`, `graphiti-all`, `observability`, `monitoring`, `websearch`, `dev`, `all`
 
 **Optional: System Dependencies**
 
@@ -245,35 +247,74 @@ The framework includes a built-in AI assistant that helps you create agents! Acc
 
 **Features:**
 - 🧠 Deep knowledge of framework documentation, examples, and source code
-- 🔍 Search tools for docs and examples
+- 🔍 **GitNexus-powered code intelligence** - 12937 symbols, 36668 relationships, 300 execution flows
 - 💡 Code generation assistance
 - 📚 Indexed knowledge base (30+ files)
 - 🗄️ Persistent knowledge graph (FalkorDB) - survives server restarts
+- 🔎 Hybrid search (semantic + structural + text fallback)
 
 **Access:** `http://localhost:8000/helper`
 
+### GitNexus Setup (Recommended)
+
+For the best experience, install and run GitNexus to enable semantic code search:
+
+```bash
+# 1. Install and index the codebase
+./scripts/setup_gitnexus.sh
+
+# 2. Start the GitNexus server
+./scripts/start_gitnexus_server.sh
+
+# 3. Verify it's running
+curl http://localhost:4747/health
+```
+
+The helper agent will automatically use GitNexus if available, with graceful fallback to text search if not running.
+
+**What GitNexus enables:**
+- Semantic code search across the entire framework
+- Full symbol context (callers, callees, imports, dependencies)
+- Execution flow tracing (300 end-to-end code paths)
+- Impact analysis and relationship queries
+
+📖 **[User Guide](docs/GITNEXUS_USER_GUIDE.md)** - Complete guide for using GitNexus features with the Helper Agent
+
+**Optional dependencies:**
+```bash
+# Install GitNexus support
+uv add agent-framework-lib[gitnexus]
+```
+
 The helper agent indexes:
 - All documentation (`docs/*.md`)
 - All examples (`examples/*.py`)
+- All builtin skills (`agent_framework/skills/builtin/skills/*/SKILL.md`)
 - Core framework source (tools, storage, memory, session management)
 
 **Re-indexing:** If you update documentation or examples, trigger a re-index:
 ```bash
+# Re-index knowledge base
 curl -X POST http://localhost:8000/helper/reindex
+
+# Re-index GitNexus (after code changes)
+npx gitnexus analyze --embeddings
 ```
 
 **Model Configuration:**
 
-By default, the helper agent uses Claude (if `ANTHROPIC_API_KEY` is set) or GPT-5.2 (if `OPENAI_API_KEY` is set). You can override this with:
+By default, the helper agent uses Claude (if `ANTHROPIC_API_KEY` is set) or GPT-5.4 (if `OPENAI_API_KEY` is set). You can override this with:
 
 ```env
 # Force a specific model (useful if your Anthropic key has reached its limit)
-HELPER_AGENT_MODEL=gpt-5.2
+HELPER_AGENT_MODEL=gpt-5.4
 ```
 
 **Example questions:**
 - "How do I create an agent with memory?"
-- "Show me how to use PDF tools"
+- "Show me the execution flow for skill loading"
+- "What calls the MemoryProvider class?"
+- "Find all code related to authentication"
 - "What's the difference between Memori and Graphiti?"
 - "How do I configure S3 storage?"
 - "Search the web for LlamaIndex best practices"

{agent_framework_lib-0.8.1.post8 → agent_framework_lib-0.8.2}/README.md

@@ -36,7 +36,7 @@ uv add agent-framework-lib[llamaindex,mcp]
 uv add agent-framework-lib[all]
 ```
 
-**Available extras:** `llamaindex`, `mcp`, `mongodb`, `elasticsearch`, `postgresql`, `s3`, `minio`, `gcp`, `multimodal`, `memory`, `memori`, `graphiti`, `graphiti-falkordb`, `graphiti-neo4j`, `graphiti-all`, `observability`, `monitoring`, `websearch`, `dev`, `all`
+**Available extras:** `llamaindex`, `mcp`, `gitnexus`, `mongodb`, `elasticsearch`, `postgresql`, `s3`, `minio`, `gcp`, `multimodal`, `memory`, `memori`, `graphiti`, `graphiti-falkordb`, `graphiti-neo4j`, `graphiti-all`, `observability`, `monitoring`, `websearch`, `dev`, `all`
 
 **Optional: System Dependencies**
 
@@ -95,35 +95,74 @@ The framework includes a built-in AI assistant that helps you create agents! Acc
 
 **Features:**
 - 🧠 Deep knowledge of framework documentation, examples, and source code
-- 🔍 Search tools for docs and examples
+- 🔍 **GitNexus-powered code intelligence** - 12937 symbols, 36668 relationships, 300 execution flows
 - 💡 Code generation assistance
 - 📚 Indexed knowledge base (30+ files)
 - 🗄️ Persistent knowledge graph (FalkorDB) - survives server restarts
+- 🔎 Hybrid search (semantic + structural + text fallback)
 
 **Access:** `http://localhost:8000/helper`
 
+### GitNexus Setup (Recommended)
+
+For the best experience, install and run GitNexus to enable semantic code search:
+
+```bash
+# 1. Install and index the codebase
+./scripts/setup_gitnexus.sh
+
+# 2. Start the GitNexus server
+./scripts/start_gitnexus_server.sh
+
+# 3. Verify it's running
+curl http://localhost:4747/health
+```
+
+The helper agent will automatically use GitNexus if available, with graceful fallback to text search if not running.
+
+**What GitNexus enables:**
+- Semantic code search across the entire framework
+- Full symbol context (callers, callees, imports, dependencies)
+- Execution flow tracing (300 end-to-end code paths)
+- Impact analysis and relationship queries
+
+📖 **[User Guide](docs/GITNEXUS_USER_GUIDE.md)** - Complete guide for using GitNexus features with the Helper Agent
+
+**Optional dependencies:**
+```bash
+# Install GitNexus support
+uv add agent-framework-lib[gitnexus]
+```
+
 The helper agent indexes:
 - All documentation (`docs/*.md`)
 - All examples (`examples/*.py`)
+- All builtin skills (`agent_framework/skills/builtin/skills/*/SKILL.md`)
 - Core framework source (tools, storage, memory, session management)
 
 **Re-indexing:** If you update documentation or examples, trigger a re-index:
 ```bash
+# Re-index knowledge base
 curl -X POST http://localhost:8000/helper/reindex
+
+# Re-index GitNexus (after code changes)
+npx gitnexus analyze --embeddings
 ```
 
 **Model Configuration:**
 
-By default, the helper agent uses Claude (if `ANTHROPIC_API_KEY` is set) or GPT-5.2 (if `OPENAI_API_KEY` is set). You can override this with:
+By default, the helper agent uses Claude (if `ANTHROPIC_API_KEY` is set) or GPT-5.4 (if `OPENAI_API_KEY` is set). You can override this with:
 
 ```env
 # Force a specific model (useful if your Anthropic key has reached its limit)
-HELPER_AGENT_MODEL=gpt-5.2
+HELPER_AGENT_MODEL=gpt-5.4
 ```
 
 **Example questions:**
 - "How do I create an agent with memory?"
-- "Show me how to use PDF tools"
+- "Show me the execution flow for skill loading"
+- "What calls the MemoryProvider class?"
+- "Find all code related to authentication"
 - "What's the difference between Memori and Graphiti?"
 - "How do I configure S3 storage?"
 - "Search the web for LlamaIndex best practices"

{agent_framework_lib-0.8.1.post8 → agent_framework_lib-0.8.2}/agent_framework/__init__.py

@@ -32,7 +32,7 @@ Example Usage:
     create_basic_agent_server(MyAgent, port=8000)
     ```
 
-Version: 0.8.1
+Version: 0.8.2
 Author: Cinco AI Team
 License: MIT
 """
@@ -88,7 +88,7 @@ def _auto_setup_dependencies() -> None:
 # Track if auto-setup has been done
 _AUTO_SETUP_DONE = False
 
-__version__ = "0.8.1"
+__version__ = "0.8.2"
 __author__ = "Cinco AI Team"
 __license__ = "MIT"
 __email__ = "sebastian@cinco.ai"

agent_framework_lib-0.8.2/agent_framework/web/docs/GITNEXUS_USER_GUIDE.md

@@ -0,0 +1,386 @@
+# GitNexus User Guide — Framework Helper Agent
+
+Le **Framework Helper Agent** utilise maintenant **GitNexus** pour une compréhension profonde du code. Ce guide explique comment tirer parti de ces nouvelles capacités.
+
+---
+
+## 🎯 Qu'est-ce que GitNexus ?
+
+GitNexus est un moteur d'intelligence de code qui indexe votre codebase dans un graphe de connaissances avec :
+
+- **13,746 symboles** (classes, fonctions, méthodes)
+- **38,427 relations** (imports, appels, héritage)
+- **300 execution flows** (processus end-to-end)
+- **6,889 embeddings** (recherche sémantique)
+
+---
+
+## ✨ Nouvelles Capacités
+
+### 1. Recherche Sémantique Intelligente
+
+**Avant GitNexus** : Recherche texte simple
+
+```
+User: Trouve comment créer un agent avec mémoire
+Helper: [Recherche grep dans les fichiers...]
+```
+
+**Avec GitNexus** : Recherche sémantique avec contexte
+
+```
+User: Trouve comment créer un agent avec mémoire
+Helper: [GitNexus query: "agent memory creation"]
+```
+
+**Résultat** :
+- Trouve les **execution flows** pertinents (agent_initialization → MemoryManager)
+- Affiche les **symboles** dans le contexte (LlamaIndexAgent, MemoryConfig)
+- Montre les **définitions** clés (MemoriProvider, GraphitiProvider)
+
+---
+
+### 2. Compréhension des Relations
+
+**Question** : Comment LlamaIndexAgent est-il utilisé ?
+
+**Réponse GitNexus** :
+
+#### Extended By (30 classes)
+- `FrameworkHelperAgent` in `agent_framework/web/helper_agent.py`
+- `SkillsDemoAgent` in `examples/skills_demo_agent.py`
+- `CalculatorAgent` in `examples/simple_agent.py`
+- ...et 27 autres
+
+#### Methods (30 méthodes)
+- `__init__` (ligne 164)
+- `get_agent_prompt` (ligne 450)
+- `get_agent_tools` (ligne 520)
+- `run_agent` (ligne 1800)
+- ...
+
+#### Imported By (8 fichiers)
+- `agent_framework/__init__.py`
+- `agent_framework/web/helper_agent.py`
+- ...
+
+---
+
+### 3. Traçage des Execution Flows
+
+**Question** : Comment fonctionne le streaming de messages ?
+
+**Résultat GitNexus** :
+
+```
+Execution Flow: "Message_stream → Agent_run"
+  Priority: 0.95
+  Steps: 12
+
+  Step 1: stream() in server.py:1566
+  Step 2: run_agent() in llamaindex_agent.py:1800
+  Step 3: _default_run_agent_stream() in llamaindex_agent.py:1200
+  ...
+  Step 12: yield TextOutputPart in agent_interface.py:250
+```
+
+---
+
+## 📖 Comment Utiliser GitNexus
+
+### Questions à Poser au Helper Agent
+
+#### 🔍 Recherche de Code
+
+```
+"Comment créer un agent avec skills personnalisées ?"
+"Où est gérée la mémoire des sessions ?"
+"Comment utiliser le file storage ?"
+```
+
+→ **GitNexus** trouve les symbols, processes, et definitions pertinents
+
+---
+
+#### 🧩 Relations et Dépendances
+
+```
+"Quelles classes étendent BaseAgent ?"
+"Qui appelle la méthode initialize_agent ?"
+"Quels fichiers importent MemoryConfig ?"
+```
+
+→ **GitNexus** affiche les relations **incoming** et **outgoing**
+
+---
+
+#### 🔄 Processus et Flows
+
+```
+"Trace l'exécution complète d'un message user"
+"Montre le flow de création d'un agent"
+"Comment fonctionne le subagent executor ?"
+```
+
+→ **GitNexus** trouve les **execution flows** step-by-step
+
+---
+
+## 🎛️ Outils Disponibles dans Helper Agent
+
+Le Helper Agent a maintenant accès à ces outils GitNexus :
+
+### 1. `search_knowledge(query)`
+
+Recherche sémantique dans le code.
+
+**Exemple** :
+```python
+search_knowledge("agent memory initialization")
+```
+
+**Retourne** :
+- Execution flows pertinents
+- Symboles dans le contexte
+- Définitions clés
+
+---
+
+### 2. `get_code_relationships(class_name)`
+
+Obtient le contexte complet d'un symbole (360° view).
+
+**Exemple** :
+```python
+get_code_relationships("LlamaIndexAgent")
+```
+
+**Retourne** :
+- Extended By (qui hérite de cette classe)
+- Imported By (qui l'importe)
+- Methods (méthodes définies)
+- Calls (quelles fonctions elle appelle)
+
+---
+
+## 🚀 Bonnes Pratiques
+
+### ✅ Bonnes Questions
+
+❌ **Trop vague** : "Comment fonctionne le framework ?"
+✅ **Spécifique** : "Comment créer un agent avec MemoriProvider ?"
+
+❌ **Trop large** : "Montre-moi tout sur les skills"
+✅ **Ciblé** : "Comment charger dynamiquement une skill personnalisée ?"
+
+---
+
+### ✅ Utiliser les Noms de Symboles
+
+Si vous connaissez le nom d'une classe/fonction :
+
+```
+"Montre-moi le contexte de MemoryConfig"
+"Qui utilise la classe SubagentExecutor ?"
+"Trace les appels vers run_agent()"
+```
+
+→ GitNexus donnera un **contexte précis** avec toutes les relations
+
+---
+
+### ✅ Demander des Exemples
+
+```
+"Montre un exemple d'agent qui utilise Graphiti"
+"Donne-moi un exemple d'utilisation de file storage"
+```
+
+→ GitNexus trouvera les **execution flows** et **process symbols** dans les exemples
+
+---
+
+## 📊 Monitoring (pour les administrateurs)
+
+### Endpoint de Health Check
+
+```bash
+curl http://localhost:4747/health/gitnexus
+```
+
+**Réponse** :
+```json
+{
+  "status": "healthy",
+  "available": true,
+  "index_fresh": true,
+  "metrics": {
+    "calls": 150,
+    "successes": 148,
+    "failures": 2,
+    "success_rate": 98.67,
+    "avg_response_time": 0.245,
+    "graphiti_fallbacks": 1,
+    "text_fallbacks": 0
+  },
+  "index": {
+    "is_fresh": true,
+    "commits_behind": 0,
+    "needs_reindex": false
+  }
+}
+```
+
+---
+
+### Logs Périodiques
+
+Toutes les 5 minutes (configurable via `GITNEXUS_METRICS_INTERVAL`), le serveur log :
+
+```
+[GITNEXUS METRICS] Calls: 150 (✅ 148, ❌ 2),
+Success rate: 98.7%, Avg response: 0.25s,
+Fallbacks: Graphiti=1, Text=0
+```
+
+**Variables d'environnement** :
+- `GITNEXUS_METRICS_LOGGING=true` (activer/désactiver)
+- `GITNEXUS_METRICS_INTERVAL=300` (intervalle en secondes)
+
+---
+
+## 🔧 Maintenance
+
+### Index Obsolète ?
+
+Si vous voyez :
+
+```
+⚠️  Index obsolète (3 commits behind)
+```
+
+**Solution** :
+```bash
+gitnexus analyze --embeddings
+```
+
+Ou : les **Git hooks** le font automatiquement après chaque commit/merge.
+
+---
+
+### Embeddings Manquants ?
+
+Si `embeddings: 0` dans `.gitnexus/meta.json` :
+
+```bash
+gitnexus analyze --embeddings
+```
+
+⚠️ **Important** : Toujours utiliser `--embeddings` pour la recherche sémantique.
+
+---
+
+## 🎓 Exemples d'Utilisation
+
+### Exemple 1 : Créer un Agent avec Mémoire
+
+**Question** :
+```
+Comment créer un agent qui se souvient des préférences utilisateur ?
+```
+
+**GitNexus trouve** :
+1. Execution flow: `Agent_initialization → MemoryManager`
+2. Symboles: `MemoryConfig`, `MemoriProvider`
+3. Exemple: `examples/agent_with_personalization.py`
+
+**Helper Agent répond** :
+```python
+# Exemple trouvé par GitNexus
+from agent_framework import LlamaIndexAgent
+from agent_framework.memory.config import MemoryConfig
+
+class MyAgent(LlamaIndexAgent):
+    def __init__(self):
+        super().__init__(
+            memory_config=MemoryConfig.memori(
+                db_url="sqlite:///agent_memory.db"
+            )
+        )
+
+    def get_agent_prompt(self) -> str:
+        return "You are an assistant that remembers user preferences..."
+```
+
+---
+
+### Exemple 2 : Comprendre le File Storage
+
+**Question** :
+```
+Montre-moi comment fonctionne le file storage dans le framework
+```
+
+**GitNexus trouve** :
+1. Class: `FileStorageManager` in `agent_framework/storage/file_storage.py`
+2. Extended by: 12 agents dans les examples
+3. Methods: `save_file()`, `get_file()`, `list_files()`
+
+**Helper Agent répond** :
+```
+Le FileStorageManager gère le stockage des fichiers générés par les agents.
+
+Utilisation :
+1. Backends supportés : local, S3, MinIO, GCP
+2. Auto-injecté dans les agents via set_file_storage()
+3. Accessible dans les tools via self.file_storage
+
+Exemple : examples/agent_with_file_storage.py
+```
+
+---
+
+## 🆘 Dépannage
+
+### GitNexus non disponible
+
+**Symptôme** : `⚠️  GitNexus non disponible - fallback to Graphiti`
+
+**Causes** :
+1. GitNexus non installé → `npm install -g gitnexus`
+2. Index non créé → `./scripts/setup_gitnexus.sh`
+3. Serveur non démarré (optionnel pour CLI)
+
+---
+
+### Requêtes lentes
+
+**Symptôme** : `avg_response_time > 2s`
+
+**Solutions** :
+1. Vérifier les embeddings : `cat .gitnexus/meta.json | grep embeddings`
+2. Re-indexer : `gitnexus analyze --embeddings`
+3. Réduire la taille du repo avec `.gitignore`
+
+---
+
+## 📚 Ressources
+
+- **Documentation GitNexus** : [https://gitnexus.io](https://gitnexus.io)
+- **CLAUDE.md** : Guide GitNexus pour Claude Code
+- **README.md** : Setup instructions
+- **CHANGELOG.md** : Historique des fonctionnalités
+
+---
+
+## ✅ Checklist pour les Utilisateurs
+
+- [ ] GitNexus installé (`gitnexus --version`)
+- [ ] Index créé avec embeddings (`.gitnexus/lbug` existe)
+- [ ] Git hooks installés (`./scripts/install_git_hooks.sh`)
+- [ ] Testé avec Helper Agent (question simple)
+- [ ] Vérifié les métriques (`curl localhost:4747/health/gitnexus`)
+
+---
+
+**Happy coding with GitNexus! 🚀**

{agent_framework_lib-0.8.1.post8 → agent_framework_lib-0.8.2}/agent_framework/web/docs/README.md

@@ -36,7 +36,7 @@ uv add agent-framework-lib[llamaindex,mcp]
 uv add agent-framework-lib[all]
 ```
 
-**Available extras:** `llamaindex`, `mcp`, `mongodb`, `elasticsearch`, `postgresql`, `s3`, `minio`, `gcp`, `multimodal`, `memory`, `memori`, `graphiti`, `graphiti-falkordb`, `graphiti-neo4j`, `graphiti-all`, `observability`, `monitoring`, `websearch`, `dev`, `all`
+**Available extras:** `llamaindex`, `mcp`, `gitnexus`, `mongodb`, `elasticsearch`, `postgresql`, `s3`, `minio`, `gcp`, `multimodal`, `memory`, `memori`, `graphiti`, `graphiti-falkordb`, `graphiti-neo4j`, `graphiti-all`, `observability`, `monitoring`, `websearch`, `dev`, `all`
 
 **Optional: System Dependencies**
 
@@ -95,35 +95,74 @@ The framework includes a built-in AI assistant that helps you create agents! Acc
 
 **Features:**
 - 🧠 Deep knowledge of framework documentation, examples, and source code
-- 🔍 Search tools for docs and examples
+- 🔍 **GitNexus-powered code intelligence** - 12937 symbols, 36668 relationships, 300 execution flows
 - 💡 Code generation assistance
 - 📚 Indexed knowledge base (30+ files)
 - 🗄️ Persistent knowledge graph (FalkorDB) - survives server restarts
+- 🔎 Hybrid search (semantic + structural + text fallback)
 
 **Access:** `http://localhost:8000/helper`
 
+### GitNexus Setup (Recommended)
+
+For the best experience, install and run GitNexus to enable semantic code search:
+
+```bash
+# 1. Install and index the codebase
+./scripts/setup_gitnexus.sh
+
+# 2. Start the GitNexus server
+./scripts/start_gitnexus_server.sh
+
+# 3. Verify it's running
+curl http://localhost:4747/health
+```
+
+The helper agent will automatically use GitNexus if available, with graceful fallback to text search if not running.
+
+**What GitNexus enables:**
+- Semantic code search across the entire framework
+- Full symbol context (callers, callees, imports, dependencies)
+- Execution flow tracing (300 end-to-end code paths)
+- Impact analysis and relationship queries
+
+📖 **[User Guide](docs/GITNEXUS_USER_GUIDE.md)** - Complete guide for using GitNexus features with the Helper Agent
+
+**Optional dependencies:**
+```bash
+# Install GitNexus support
+uv add agent-framework-lib[gitnexus]
+```
+
 The helper agent indexes:
 - All documentation (`docs/*.md`)
 - All examples (`examples/*.py`)
+- All builtin skills (`agent_framework/skills/builtin/skills/*/SKILL.md`)
 - Core framework source (tools, storage, memory, session management)
 
 **Re-indexing:** If you update documentation or examples, trigger a re-index:
 ```bash
+# Re-index knowledge base
 curl -X POST http://localhost:8000/helper/reindex
+
+# Re-index GitNexus (after code changes)
+npx gitnexus analyze --embeddings
 ```
 
 **Model Configuration:**
 
-By default, the helper agent uses Claude (if `ANTHROPIC_API_KEY` is set) or GPT-5.2 (if `OPENAI_API_KEY` is set). You can override this with:
+By default, the helper agent uses Claude (if `ANTHROPIC_API_KEY` is set) or GPT-5.4 (if `OPENAI_API_KEY` is set). You can override this with:
 
 ```env
 # Force a specific model (useful if your Anthropic key has reached its limit)
-HELPER_AGENT_MODEL=gpt-5.2
+HELPER_AGENT_MODEL=gpt-5.4
 ```
 
 **Example questions:**
 - "How do I create an agent with memory?"
-- "Show me how to use PDF tools"
+- "Show me the execution flow for skill loading"
+- "What calls the MemoryProvider class?"
+- "Find all code related to authentication"
 - "What's the difference between Memori and Graphiti?"
 - "How do I configure S3 storage?"
 - "Search the web for LlamaIndex best practices"