LiteLLM Minor Fixes & Improvements (11/21/2024)

Title

Fix Vertex AI function calling invoke: use JSON format instead of protobuf text format. Merge https://github.com/BerriAI/litellm/pull/6702
fix(openai_like/handler.py): return more descriptive error message
docs(anthropic.md): update anthropic docs to show how to route to any new model
feat(groq/): fake stream when 'response_format' param is passed
feat(groq/): add response_format support for groq
fix(o1_handler.py): remove fake streaming for o1
build(model_prices_and_context_window.json): add groq llama3.2b model pricing
fix(utils.py): fix handling ollama response format param
docs(sidebars.js): refactor chat endpoint placement

Relevant issues

Fixes https://github.com/BerriAI/litellm/issues/6812 Groq doesn't support streaming when response_format is set Closes https://github.com/BerriAI/litellm/issues/6845 Closes https://github.com/BerriAI/litellm/issues/6801 Closes https://github.com/BerriAI/litellm/issues/6807 Fixes https://github.com/BerriAI/litellm/issues/6848 Fixes https://github.com/BerriAI/litellm/issues/6833

Type

🆕 New Feature 🐛 Bug Fix 🧹 Refactoring 📖 Documentation 🚄 Infrastructure ✅ Test

Changes

[REQUIRED] Testing - Attach a screenshot of any new tests passing locall

If UI changes, send a screenshot/GIF of working UI fixes

Description by Korbit AI

What change is being made?

Refactor the FunctionCall structure by simplifying the creation and restructuring of arguments dictionaries across litellm and update associated tests to handle tool calls with no arguments.

Why are these changes being made?

These changes are made to streamline code by eliminating unnecessary structures like Field and FunctionCallArgs, simplifying how function calls are constructed. This refactor enhances the maintainability and readability of the function call code. Additionally, the updates to the test cases ensure that functionality, such as handling tool calls with no arguments (as per GitHub issue #6833), is covered by testing to prevent future regressions.

Is this description stale? Ask me to generate a new description by commenting /korbit-generate-pr-description

BerriAI / litellm