Truncate message logs to below max supported prompt size by model

- Use tiktoken to count tokens for chat models
- Make conversation turns to add to prompt configurable via method
  argument to generate_chatml_messages_with_context method

pyproject.toml

@@ -41,6 +41,7 @@ dependencies = [
     "fastapi == 0.77.1",
     "jinja2 == 3.1.2",
     "openai >= 0.27.0",
+    "tiktoken >= 0.3.0",
     "pillow == 9.3.0",
     "pydantic == 1.9.1",
     "pyqt6 == 6.3.1",