feat: implement RAG capabilities and Context Pane integration

- Add RAG capabilities using LlamaIndex and ChromaDB
- Implement RAGManager for PHB indexing and retrieval
- Integrate RAG pipeline into orchestrator to trigger queries based on extracted entities
- Update TUI to include a 3-column layout with a real-time Context Pane
- Define ContextUpdate data models in src/llm/models.py
- Update requirements.txt with new dependencies

src/llm/models.py

@@ -44,6 +44,16 @@ class CharacterStateUpdate(BaseModel):
     )
 
 
+class ContextUpdate(BaseModel):
+    query: str = Field(..., description="The search query used to retrieve the context")
+    snippet: str = Field(
+        ..., description="The relevant text snippet retrieved from the source"
+    )
+    source: str = Field(
+        ..., description="The source of the snippet (e.g., 'PHB p. 12')"
+    )
+
+
 class ExtractionResult(BaseModel):
     lore_updates: List[LoreUpdate] = Field(
         default_factory=list, description="List of discovered lore facts", alias="lore"