| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2024-09-02 | feat: migrate `cloudflare` client to `openai-compatible` (#821) | sigoden | -0/+1 | |
| 2024-09-02 | chore: update models.yaml | sigoden | -108/+95 | |
| 2024-09-01 | refactor: minor improvement (#818) | sigoden | -178/+181 | |
| 2024-08-31 | refactor: update models.yaml to fix Bedrock Sonnet 3.5 max_output_tokens ↵ | rolfwilms | -1/+1 | |
| (4096) (#813) | ||||
| 2024-08-24 | feat: support ai21 client (#800) | sigoden | -4/+29 | |
| 2024-08-22 | chore: update models.yaml | sigoden | -7/+7 | |
| 2024-08-22 | refactor: update models.yaml (#799) | sigoden | -82/+157 | |
| 2024-08-22 | feat: support github client (#798) | sigoden | -0/+38 | |
| 2024-08-01 | refactor: update models.yaml (#772) | sigoden | -23/+35 | |
| 2024-07-31 | refactor: update models.yaml and make minor improvement (#771) | sigoden | -4/+8 | |
| 2024-07-28 | refactor: udpate models.yaml and Argcfile.sh (#761) | sigoden | -20/+22 | |
| 2024-07-27 | feat: bedrock client switch to converse api and support cohere models (#747) | sigoden | -23/+36 | |
| 2024-07-26 | feat: vertexai support mistral models (#746) | sigoden | -1/+15 | |
| 2024-07-26 | feat: merge vertexai-cluade with vertexai (#745) | sigoden | -21/+15 | |
| 2024-07-25 | chore: update models.yaml (#743) | sigoden | -31/+32 | |
| 2024-07-24 | refactor: update models.yaml (#739) | sigoden | -219/+224 | |
| 2024-07-19 | refactor: update models.yaml (#726) | sigoden | -1/+31 | |
| 2024-07-11 | refactor: update models.yaml and abandon anyscale (#701) | sigoden | -66/+33 | |
| 2024-07-02 | chore: update models.yaml | sigoden | -60/+7 | |
| 2024-06-29 | refactor: update models.yaml (#669) | sigoden | -10/+6 | |
| 2024-06-25 | refactor: rename model type `rerank` to `reranker` (#646) | sigoden | -9/+10 | |
| 2024-06-25 | feat: support rag-dedicated clients (jina and voyageai) (#645) | sigoden | -1/+108 | |
| 2024-06-23 | refactor: embedding model add price and dimension (#636) | sigoden | -24/+68 | |
| 2024-06-23 | refactor: remove reka client (#635) | sigoden | -22/+0 | |
| 2024-06-23 | refactor: improve system message handling (#634) | sigoden | -6/+5 | |
| 2024-06-22 | feat: ernie support function calling (#631) | sigoden | -0/+2 | |
| 2024-06-22 | feat: ernie support embeddings and rereank (#630) | sigoden | -0/+23 | |
| 2024-06-22 | refactor: update readme and models.yaml | sigoden | -43/+19 | |
| 2024-06-21 | refactor: rename model.max_concurrent_chunks to model.max_batch_size (#626) | sigoden | -32/+32 | |
| 2024-06-21 | refactor: rename model.mode to model.type (#625) | sigoden | -35/+35 | |
| 2024-06-21 | feat: cloudflare support embeddings (#623) | sigoden | -14/+34 | |
| 2024-06-21 | refactor: update models.yaml | sigoden | -96/+206 | |
| 2024-06-21 | refactor: update models.yaml (#621) | sigoden | -0/+24 | |
| 2024-06-21 | feat: support rerank (#620) | sigoden | -0/+6 | |
| 2024-06-19 | refactor: rag add rag_minimum_score config (#617) | sigoden | -0/+9 | |
| 2024-06-19 | feat: qianwen support function calling (#616) | sigoden | -3/+3 | |
| 2024-06-18 | feat: support reka client (#614) | sigoden | -0/+22 | |
| 2024-06-18 | feat: support lingyiwanwu client (#613) | sigoden | -0/+35 | |
| 2024-06-15 | refactor: update models.yaml (#602) | sigoden | -190/+156 | |
| 2024-06-14 | refactor: add/modify rag-related config (#599) | sigoden | -2/+2 | |
| 2024-06-12 | refactor: rag default_chunk_size (#588) | sigoden | -5/+5 | |
| 2024-06-05 | refactor: rename `pass_max_tokens` to `require_max_tokens` (#562) | sigoden | -32/+32 | |
| 2024-06-05 | feat: support RAG (#560) | sigoden | -0/+43 | |
| * feat: support RAG * support more embeddings models and implement concurrent embedding api * show the progress of addings paths * ignore embedding context when saving message * embedding model max_chunk_size => default_chunk_size * support pdf and pandoc formats (docx, epub, ipynb) | ||||
| 2024-05-26 | fix: bedrock issues (#544) | rolfwilms | -2/+2 | |
| * Removed extraneous key [stream] for AWS Bedrock Claude models. * Reduceddefault AWS Bedrock llama-3 max_output_tokens to 2048 to align with API requirements. --------- Co-authored-by: Rolf Wilms <rwilms@csc.com> | ||||
| 2024-05-23 | refactor: qiawen client add qwen-long (#537) | sigoden | -11/+17 | |
| 2024-05-18 | feat: support function calling (#514) | sigoden | -2/+23 | |
| * feat: support function calling * fix on Windows OS * implement multi-steps function calling * fix on Windows OS * add error for client not support function calling * refactor message data structure and make claude client supporting function calling * support reuse previous call results * improve error handling for function calling * use prefix `may_` as indicator for `execute` type fucntions | ||||
| 2024-05-15 | refactor: add gemini-1.5-flash to models.yaml (#510) | sigoden | -5/+17 | |
| 2024-05-14 | refactor: minor refinement | sigoden | -1/+1 | |
| 2024-05-14 | refactor: update models.yaml (#501) | sigoden | -8/+15 | |
| 2024-05-08 | refactor: model pass_max_tokens (#493) | sigoden | -28/+64 | |
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |
path: root/models.yaml