feat: add Ollama runtime support and RAG implementation plan

Ollama Runtime:
- Add ollama_client.py for Ollama API integration
- Support for dots-ocr model via Ollama
- Add OLLAMA_BASE_URL configuration
- Update inference.py to support Ollama runtime (RUNTIME_TYPE=ollama)
- Update endpoints to handle async Ollama calls
- Alternative to local transformers model

RAG Implementation Plan:
- Create TODO-RAG.md with detailed Haystack integration plan
- Document Store setup (pgvector)
- Embedding model selection
- Ingest pipeline (PARSER → RAG)
- Query pipeline (RAG → LLM)
- Integration with DAGI Router
- Bot commands (/upload_doc, /ask_doc)
- Testing strategy

Now supports three runtime modes:
1. Local transformers (RUNTIME_TYPE=local)
2. Ollama (RUNTIME_TYPE=ollama)
3. Dummy (USE_DUMMY_PARSER=true)

services/parser-service/app/core/config.py

@@ -37,9 +37,12 @@ class Settings(BaseSettings):
     ALLOW_DUMMY_FALLBACK: bool = os.getenv("ALLOW_DUMMY_FALLBACK", "true").lower() == "true"
     
     # Runtime
-    RUNTIME_TYPE: Literal["local", "remote"] = os.getenv("RUNTIME_TYPE", "local")
+    RUNTIME_TYPE: Literal["local", "remote", "ollama"] = os.getenv("RUNTIME_TYPE", "local")
     RUNTIME_URL: str = os.getenv("RUNTIME_URL", "http://parser-runtime:11435")
     
+    # Ollama configuration (if RUNTIME_TYPE=ollama)
+    OLLAMA_BASE_URL: str = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
+    
     class Config:
         env_file = ".env"
         case_sensitive = True