| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2024-10-19 | feat: support openai o1 models (#935) | sigoden | -0/+12 | |
| 2024-09-03 | feat: use dynamic batch size for embedding (#826) | sigoden | -6/+11 | |
| 2024-09-01 | refactor: minor improvement (#818) | sigoden | -6/+1 | |
| 2024-08-16 | feat: no check model's support for function calls (#791) | sigoden | -4/+0 | |
| 2024-07-27 | feat: abandon AICHAT_PLATFORM and several improvements (#752) | sigoden | -3/+3 | |
| 2024-07-26 | refactor: several optimizations (#749) | sigoden | -8/+0 | |
| 2024-06-25 | refactor: rename model type `rerank` to `reranker` (#646) | sigoden | -4/+4 | |
| 2024-06-23 | refactor: embedding model add price and dimension (#636) | sigoden | -29/+51 | |
| 2024-06-21 | refactor: rename model.max_concurrent_chunks to model.max_batch_size (#626) | sigoden | -6/+6 | |
| 2024-06-21 | refactor: rename model.mode to model.type (#625) | sigoden | -5/+5 | |
| 2024-06-21 | feat: serve embeddings api (#624) | sigoden | -2/+2 | |
| 2024-06-21 | feat: support rerank (#620) | sigoden | -3/+10 | |
| 2024-06-14 | refactor: add/modify rag-related config (#599) | sigoden | -2/+9 | |
| 2024-06-11 | feat: support bot (#579) | sigoden | -5/+18 | |
| * feat: support bots * refactor with RoleLike * improve exiting session * make bot works with rag * refactor repl assert state * add bot banner * repl complete bots according bots.txt * fix on windows * remove threadpool executing function callings * adjust repl left_prompt * move bot config to global config.yaml * `.bot` throw err if funciton callings is not configured | ||||
| 2024-06-05 | refactor: rename `pass_max_tokens` to `require_max_tokens` (#562) | sigoden | -4/+4 | |
| 2024-06-05 | feat: support RAG (#560) | sigoden | -5/+39 | |
| * 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) | ||||
| 2024-05-22 | feat: allow patching req body with client config (#534) | sigoden | -21/+0 | |
| 2024-05-18 | feat: support function calling (#514) | sigoden | -106/+90 | |
| * 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 | ||||
| 2024-05-14 | feat: remove tiktoken (#506) | sigoden | -2/+2 | |
| 2024-05-08 | refactor: model pass_max_tokens (#493) | sigoden | -20/+20 | |
| 2024-05-07 | feat: support playground/arena webui (#487) | sigoden | -0/+4 | |
| 2024-05-02 | chore: clippy | sigoden | -1/+1 | |
| 2024-04-30 | feat: openai-compatible platforms share the same client (#469) | sigoden | -0/+6 | |
| 2024-04-30 | feat: add `.set max_output_tokens` (#468) | sigoden | -12/+17 | |
| 2024-04-29 | feat: `.model` repl completions show max tokens and price (#462) | sigoden | -5/+57 | |
| 2024-04-29 | refactor: user config models replace client builtin models | sigoden | -11/+2 | |
| 2024-04-29 | refactor: merge config models, update client models (#460) | sigoden | -2/+11 | |
| 2024-04-28 | refactor: extract prelude models to models.yaml (#451) | sigoden | -45/+24 | |
| 2024-04-25 | refactor: rewrite list models of all clients (#436) | sigoden | -11/+0 | |
| 2024-04-23 | feat: builtin models can be overwrited by models config (#429) | sigoden | -13/+24 | |
| 2024-04-23 | feat: customize model's max_output_tokens (#428) | sigoden | -3/+37 | |
| 2024-04-11 | refactor: all clients use openai token counter (#402) | sigoden | -13/+5 | |
| 2024-03-06 | refactor: rename model's `max_tokens` to `max_input_tokens` (#339) | sigoden | -11/+11 | |
| BREAKING CHANGE: rename model's `max_tokens` to `max_input_tokens` | ||||
| 2024-01-30 | feat: add `extra_fields` to models of localai/ollama clients (#298) | Kelvie Wong | -0/+21 | |
| * Add an "extra_fields" config to localai models Because there are so many local AIs out there with a bunch of custom parameters you can set, this allows users to send in extra parameters to a local LLM runner, such as, e.g. `instruction_template: Alpaca`, so that Mixtral can take a system prompt. * support ollama --------- Co-authored-by: sigoden <sigoden@gmail.com> | ||||
| 2024-01-13 | feat: supports model capabilities (#297) | sigoden | -0/+51 | |
| 1. automatically switch to the model that has the necessary capabilities. 2. throw an error if the client does not have a model with the necessary capabilities | ||||
| 2023-11-27 | feat: support vision (#249) | sigoden | -2/+10 | |
| * feat: support vision * clippy * implement vision * resolve data url to local file * add model openai:gpt-4-vision-preview * use newline to concate embeded text files * set max_tokens for gpt-4-vision-preview | ||||
| 2023-11-07 | feat: allow the use of an unlisted model (#219) | sigoden | -0/+31 | |
| 2023-11-07 | refactor: remove Model.client_index, match client by name (#218) | sigoden | -4/+2 | |
| 2023-11-07 | refactor: rename Model.llm_name to name (#216) | sigoden | -3/+3 | |
| 2023-11-03 | refactor: improve code quanity (#203) | sigoden | -0/+80 | |
| - update field name of ModelInfo - rename ModelInfo to Model | ||||
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |