Pinned issues
Issues
- 1
Interim and Long term plans?
#349 opened by mweichert - 1
Ollama Llama3.1
#348 opened by prpanto - 2
- 0
TypeValidationError - Seems like if there are issue with OpenAI, it is still trying to call chat completion and giving type error
#344 opened by lcsvcn - 1
Update docs to include `response_format` for OpenAI ChatTextGenerator; `responseFormat` is supported but not documented
#339 opened by mrprkr - 1
Path with space in causes problem
#334 opened by richardgroves - 0
Anthropic Claude Support
#332 opened by parzival418 - 0
- 0
- 0
Add support for gpt-4-turbo model
#326 opened by fcam77 - 3
Google Gemini exploration
#244 opened by jakedetels - 0
Cannot pass custom parameters to the provider
#306 opened by snowyu - 3
Ollama Mistral .withPromptTemplate Error
#285 opened by joshon - 0
Cohere custom model and chat api support
#238 opened by jakedetels - 7
experimental-vm-modules bug introduced in v0.134.0
#278 opened by jakedetels - 4
- 3
First parameter has member `readable` when running generate text on AWS Lambda.
#263 opened by Morphexe - 0
introduce classify model function
#246 opened by jakedetels - 2
Node llama.cpp bindings
#234 opened by nnance - 1
Tools do not work with ollama
#254 opened by ColtonMcInroy - 1
- 0
- 0
explore variable output parsers, e.g. for list (when generated using GBNF grammar)
#250 opened by jakedetels - 0
- 0
Perplexity LLM exploration and docs page (OpenAI compatible should work) - they have online LLMs which are cool
#241 opened by jakedetels - 0
LocalAI exploration & docs page (OpenAI)
#242 opened by jakedetels - 2
Help wanted: Improve documentation
#171 opened by lgrammel - 0
Help wanted: Add tutorials and recipes
#170 opened by lgrammel - 0
move out openai cost calc from modelfusion and modelfusion/experimental into a standalone pkg that can also be used w/o modelfusion
#248 opened by jakedetels - 0
Add OpenChat prompt template
#245 opened by jakedetels - 0
explore img + text -> image models / prompts
#247 opened by jakedetels - 0
TurboPuff Vector DB support
#239 opened by jakedetels - 1
Postgres/Knex Vector DB support with pgvector
#240 opened by jakedetels - 2
original model response not available when setting `fullResponse` to true in `streamText()`.
#215 opened by jakedetels - 2
Add postgres / knex vector db
#131 opened by lgrammel - 0
Add Anthropic tokenizer
#134 opened by lgrammel - 3
Caching fails on subsequent invocations
#235 opened by jakedetels - 6
Add support for Ollama multimodal
#190 opened by suavelizard - 6
Code execution tool
#137 opened by sahanxdissanayake - 3
Embedding with AzureOpenAI
#194 opened by nanotronic - 11
Deno Compatibility
#188 opened by 7flash - 0
Support parallel tool calls and JSON guarantees
#175 opened by lgrammel - 1
OpenAI Azure streaming does not work
#185 opened by lgrammel - 6
- 2
No longer can use on browser only v0.63.0
#168 opened by Necmttn - 2
Support sqlite vector search module
#157 opened by bjsi - 10
llama.cpp server / embeddings broken
#156 opened by skadefro - 0
Add replicate provider
#130 opened by lgrammel - 2
- 5
Support ElevenLabs text to speech websockets
#141 opened by bjsi