| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2024-02-05 | fix: do not attempt to deserialize zero byte chunks in ollama stream (#303) | Joseph Goulden | -0/+3 | |
| 2024-01-30 | feat: add `extra_fields` to models of localai/ollama clients (#298) | Kelvie Wong | -2/+28 | |
| * 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> | ||||
| 2024-01-30 | feat: add openai.api_base config (#302) | sigoden | -6/+3 | |
| 2024-01-13 | feat: supports model capabilities (#297) | sigoden | -103/+159 | |
| 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 | ||||
| 2023-12-25 | refactor: ollam api_base configuration (#285) | sigoden | -1/+1 | |
| 2023-12-24 | feat: custom REPL prompt (#283) | sigoden | -2/+2 | |
| 2023-12-20 | feat: qianwen vision models support embeded images (#277) | sigoden | -19/+128 | |
| 2023-12-20 | feat: support ollama (#276) | sigoden | -1/+211 | |
| 2023-12-19 | feat: support qianwen:qwen-vl-plus (#275) | sigoden | -48/+121 | |
| 2023-12-19 | refactor: adjust order of ernie models | sigoden | -2/+2 | |
| 2023-12-19 | feat: abandon PaLM2 (#274) | sigoden | -132/+1 | |
| 2023-12-19 | feat: support gemini (#273) | sigoden | -19/+260 | |
| 2023-12-16 | chore: change order of openai models | sigoden | -2/+2 | |
| 2023-11-27 | feat: add ernie:ernie-bot-8k qianwen:qwen-max (#252) | sigoden | -15/+16 | |
| 2023-11-27 | feat: support vision (#249) | sigoden | -23/+104 | |
| * 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 | ||||
| 2023-11-14 | refactor: palm client system message (#245) | sigoden | -8/+5 | |
| 2023-11-14 | refactor: ernie client system message (#244) | sigoden | -6/+5 | |
| 2023-11-09 | refactor: qianwen client use incremental_output (#240) | sigoden | -5/+5 | |
| 2023-11-08 | refactor: improve code quanity (#238) | sigoden | -5/+1 | |
| 2023-11-08 | feat: add openai:gpt-4-1106-preview (#233) | sigoden | -2/+4 | |
| 2023-11-07 | feat: allow the use of an unlisted model (#219) | sigoden | -0/+43 | |
| 2023-11-07 | refactor: remove Model.client_index, match client by name (#218) | sigoden | -41/+32 | |
| 2023-11-07 | refactor: use &GlobalConfig to avoid clone (#217) | sigoden | -4/+4 | |
| 2023-11-07 | refactor: rename Model.llm_name to name (#216) | sigoden | -12/+12 | |
| 2023-11-06 | refactor: improve error message for PaLM client (#213) | sigoden | -2/+8 | |
| 2023-11-04 | feat: support Qianwen (#211) | sigoden | -0/+161 | |
| 2023-11-04 | feat: support Ernie (#210) | sigoden | -0/+232 | |
| 2023-11-04 | feat: support PaLM (#209) | sigoden | -2/+154 | |
| 2023-11-04 | refactor: rename azure to azure_openai, improve register_client! (#208) | sigoden | -15/+20 | |
| 2023-11-03 | refactor: rename azure-openai to azure (#204) | sigoden | -28/+11 | |
| 2023-11-03 | refactor: improve code quanity (#203) | sigoden | -42/+42 | |
| - update field name of ModelInfo - rename ModelInfo to Model | ||||
| 2023-11-02 | refactor: improve repl completer (#199) | sigoden | -2/+2 | |
| 2023-11-02 | refactor: improve code quanity (#197) | sigoden | -17/+155 | |
| - move model_info.rs/message.rs to clients/ - rename SharedConfig to GlobalConfig | ||||
| 2023-11-02 | refactor: improve code quanity (#196) | sigoden | -20/+20 | |
| - rewrite Repl, remove ReplHandler - move ReplyStreamHandler to repl/ and rename it to ReplyHandler - deprecate utils::print_now - refactor session info | ||||
| 2023-11-02 | refactor: set tokens count factors (#195) | sigoden | -11/+28 | |
| 2023-11-01 | chore: spellcheck typos | sigoden | -2/+2 | |
| 2023-11-01 | refactor: improve code quanity (#194) | sigoden | -5/+9 | |
| - extends ModelInfo for tokens calculating - refactor config/session.rs, improve export, render, getter/setter - modify main.rs, allow --model override session.model | ||||
| 2023-11-01 | refactor: add/use openai_compatible_client macro | sigoden | -110/+69 | |
| 2023-11-01 | refactor: use reqwest-eventsource as sse client | sigoden | -18/+30 | |
| 2023-11-01 | refactor: clients/* and config.rs (#193) | sigoden | -464/+405 | |
| - add register_clients macro to make it easier to add a new client - no create_client_config, just add const PROMPTS - move ModelInfo from clients/ to config/ - model's max_tokens are optional - improve code quanity on config/mod.rs - add/use macro config_get_fn | ||||
| 2023-10-31 | feat: improve client (#189) | sigoden | -295/+261 | |
| 2023-10-31 | feat: support OPENAI_API_BASE (#186) | sigoden | -2/+7 | |
| 2023-10-31 | feat: support azure-openai (#166) | sigoden | -1/+197 | |
| 2023-10-30 | fix: dry run on role or session (#181) | sigoden | -5/+7 | |
| 2023-10-30 | chore: remove unnecessary clippy macros | sigoden | -4/+0 | |
| 2023-10-29 | feat: autodetect light theme on unix-like os (#168) | sigoden | -4/+3 | |
| 2023-10-29 | chore: improve client-related code quality | sigoden | -73/+55 | |
| 2023-10-28 | refactor: improve environment variables (#163) | sigoden | -16/+30 | |
| Rename `AICHAT_API_KEY` to `OPENAI_API_KEY` Add `LOCALAI_API_KEY` | ||||
| 2023-10-27 | refactor: streaming input text in dry-run mode (#154) | sigoden | -1/+6 | |
| 2023-10-26 | refactor: improve code quanity | sigoden | -23/+10 | |
| remove tokio::runtime::Runtime from client | ||||
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |