Replace Ollama with llama-server (OpenAI-compatible API)

- Update llm.py to use OpenAI client with custom base_url for llama-server
- Update agents.py to use ChatOpenAI instead of ChatOllama
- Remove unused ollama imports from main.py, chunker.py, query.py
- Add LLAMA_SERVER_URL and LLAMA_MODEL_NAME env vars
- Remove ollama and langchain-ollama dependencies

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

pyproject.toml

@@ -9,7 +9,6 @@ dependencies = [
     "python-dotenv>=1.0.0",
     "flask>=3.1.2",
     "httpx>=0.28.1",
-    "ollama>=0.6.0",
     "openai>=2.0.1",
     "pydantic>=2.11.9",
     "pillow>=10.0.0",
@@ -34,7 +33,6 @@ dependencies = [
     "langchain-chroma>=1.0.0",
     "langchain-community>=0.4.1",
     "jq>=1.10.0",
-    "langchain-ollama>=1.0.1",
     "tavily-python>=0.7.17",
 ]