trustgraph/trustgraph-flow/trustgraph/model/text_completion
Het Patel 0ef49ab6ae
feat: standardize LLM rate-limiting and exception handling (#835)
- HTTP 429 translates to TooManyRequests (retryable)
- HTTP 503 translates to LlmError
2026-04-21 16:15:11 +01:00
..
azure Use model in Azure LLM integration (#657) 2026-03-04 12:06:06 +00:00
azure_openai Fix OpenAI compatibility issues for newer models and Azure config (#727) 2026-03-28 11:19:45 +00:00
claude Feature/streaming llm phase 1 (#566) 2025-11-26 09:59:10 +00:00
cohere feat: standardize LLM rate-limiting and exception handling (#835) 2026-04-21 16:15:11 +01:00
llamafile Fix LLM metrics (#631) 2026-02-09 19:35:42 +00:00
lmstudio Fix LLM metrics (#631) 2026-02-09 19:35:42 +00:00
mistral feat: standardize LLM rate-limiting and exception handling (#835) 2026-04-21 16:15:11 +01:00
ollama Feat: Auto-pull missing Ollama models (#757) 2026-04-06 11:10:53 +01:00
openai feat: standardize LLM rate-limiting and exception handling (#835) 2026-04-21 16:15:11 +01:00
tgi Fix LLM metrics (#631) 2026-02-09 19:35:42 +00:00
vllm feat: standardize LLM rate-limiting and exception handling (#835) 2026-04-21 16:15:11 +01:00
__init__.py Feature/pkgsplit (#83) 2024-09-30 19:36:09 +01:00