Fix JSONDecodeError for Ollama and hide LiteLLM vision support warning

[CyanideByte]

Describe the changes you have made:

• Disabled function calling for ollama which fixes "json.decoder.JSONDecodeError: Unterminated string starting at: line 1 column 2 (char 1)"
• Hides a LiteLLM warning that the model doesn't support vision

Reference any relevant issues (e.g. "Fixes #000"):

• Fixes OLLAMA LLAMA 3.2 fails to run with JSON Encoding error  #1514
• Fixes Running "interpreter --model i raises a LiteLLM:ERROR #1512
• Fixes [llama-3.1 70B]Open Interpreter's Preps did not complete after setting the model #1371

Pre-Submission Checklist (optional but appreciated):

• I have included relevant documentation updates (stored in /docs)
• I have read docs/CONTRIBUTING.md
• I have read docs/ROADMAP.md

OS Tests (optional but appreciated):

• Tested on Windows
• Tested on MacOS
• Tested on Linux

[Notnaton]

#1514

[Notnaton]

Does litellm have a dict of which model/provider supports function calling?

If function call fail, should we set the --no-supports_function_calling flag automatically?