merlyn/server/utils/AiProviders
Tristan Stahnke b64a77f29f
Refactor AWS Bedrock Provider for Multi-modal Support & Correct Token Limits (#3714)
* Fixed two primary issues discovered while using AWS Bedrock with Anthropic Claude Sonnet models:
- Context Window defaults to 8192 maximum, which isn't correct
- Multimodal stopped working when removing langchain, which was transparently handling image_url to a format sonnet expects.

* Ran `yarn lint`

* Updated .env.example to have aws bedrock examples too

* Refactor for readability
move utils for AWS specific functionality to subfile
add token output max to ENV so setting persits

---------

Co-authored-by: Tristan Stahnke <tristan.stahnke+gpsec@guidepointsecurity.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2025-05-06 12:55:24 -07:00
..
anthropic Add support for Anthropics /model endpoint (finally) (#3376) 2025-02-28 13:29:43 -08:00
apipie Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
azureOpenAi Replace @azure/openai with openai, and update openai to version 4.95.1 (#3691) 2025-04-29 11:21:39 -07:00
bedrock Refactor AWS Bedrock Provider for Multi-modal Support & Correct Token Limits (#3714) 2025-05-06 12:55:24 -07:00
cohere LLM performance metric tracking (#2825) 2024-12-16 14:31:17 -08:00
deepseek Add tokenizer improvments via Singleton class and estimation (#3072) 2025-01-30 17:55:03 -08:00
fireworksAi LLM performance metric tracking (#2825) 2024-12-16 14:31:17 -08:00
gemini Refactor Gemini to use OpenAI interface API (#3616) 2025-04-07 17:18:31 -07:00
genericOpenAi Add handling to reasoning models for Generic OpenAI connector (#3183) 2025-02-12 10:28:44 -08:00
groq Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
huggingface LLM performance metric tracking (#2825) 2024-12-16 14:31:17 -08:00
koboldCPP Add option to control KoboldCPP max response tokens (#3746) 2025-05-02 14:12:06 -07:00
liteLLM Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
lmStudio Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
localAi Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
mistral Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
novita feat: update novita AI logo and default model (#3037) 2025-01-27 08:41:12 -08:00
nvidiaNim Update NVIDIA branding 2025-01-28 10:27:31 -08:00
ollama lint 2025-02-18 20:49:40 -08:00
openAi Replace @azure/openai with openai, and update openai to version 4.95.1 (#3691) 2025-04-29 11:21:39 -07:00
openRouter linting 2025-04-15 12:51:08 -07:00
perplexity handling of citations in openRouter provider #3581 (#3620) 2025-04-15 10:57:09 -07:00
ppio Add new model provider PPIO (#3211) 2025-02-27 10:53:00 -08:00
textGenWebUI Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
togetherAi Dynamic fetching of TogetherAI models (#3017) 2025-01-24 11:06:59 -08:00
xai Support historical message image inputs/attachments for n+1 queries (#2919) 2025-01-16 13:49:06 -08:00
modelMap.js Update Azure AI options and model map with new model configurations (#3660) 2025-04-16 09:08:40 -07:00