summaryrefslogtreecommitdiff
path: root/py (follow)
Commit message (Collapse)AuthorAgeFiles
* Ensure role config file exists before loading to prevent errorsKonfekt2024-03-101
| | | | | | | | | | | The problem was that the application tried to load a roles configuration file without checking whether it actually exists, potentially leading to unhandled exceptions if the file is missing. Ensure that the roles configuration file exists before attempting to read from it; raise an exception with a clear message if the file is not found. diff --git a/py/roles.py b/py/roles.py: -if not os.path.exists(roles_config_path): - raise Exception(f"Role config file does not exist: {roles_config_path}") -
* supprot config only rolesMartin Bielik2024-03-091
|
* simple error handlingMartin Bielik2024-03-091
|
* fix using role in existing chatMartin Bielik2024-03-091
|
* roles example fileMartin Bielik2024-03-092
|
* roles completionMartin Bielik2024-03-091
|
* parse role optionsMartin Bielik2024-03-093
|
* read role prompt from configMartin Bielik2024-03-093
|
* removed config path logMartin Bielik2024-03-091
|
* feat: add an option to customize api key file locationjiangyinzuo2024-03-081
|
* feat(chat): add `include` role to include filesJason Kölker2024-01-241
| | | | | | | | | | | | | | | | | | | | | | | | | Files may be included in the chat by a special `include` role. Each file's contents will be added to an additional `user` role message with the files separated by `==> {path} <==` where `{path}` is the path to the file. Globbing is expanded out via `glob.glob` and relative apths to the current working directory (as determined by `getcwd()`) will be resolved to absolute paths. Example: ``` >>> user Generate documentation for the following files >>> include /home/user/myproject/src/../requirements.txt /home/user/myproject/**/*.py ``` Fixes: #69
* import vim before utils, fixes #43Martin Bielik2023-12-232
|
* added explaining commentMartin Bielik2023-12-021
|
* fix selection include extra content when the user is in visual modecposture2023-12-023
|
* fixed python3.12 slash escaping, fixes #61Martin Bielik2023-11-011
|
* removed unused importMartin Bielik2023-10-212
|
* Merge remote-tracking branch 'origin/main' into base-url-configMartin Bielik2023-10-211
|\
| * Include OpenAI Org ID from the token configDuy Lam2023-09-091
| |
* | endpoint_url configMartin Bielik2023-10-212
| |
* | option to disable authorizationMartin Bielik2023-10-211
| |
* | base_url extracted to config, docuMartin Bielik2023-10-212
| |
* | Add support for base_url option to use local modelsjuodumas2023-09-183
|/ | | | | | | | | | | | | | | | | | | | | | | | | | For example, you can start llama-cpp-python like this (it emulates the openai api): ```sh CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install 'llama-cpp-python[server]' wget https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGUF/resolve/main/codellama-13b-instruct.Q5_K_M.gguf python3 -m llama_cpp.server --n_gpu_layers 100 --model codellama-13b-instruct.Q5_K_M.gguf ``` Then set the API url in your `.vimrc`: ```vim let g:vim_ai_chat = { \ "engine": "chat", \ "options": { \ "base_url": "http://127.0.0.1:8000", \ }, \ } ``` And chat with the locally hosted AI using `:AIChat`. The change in utils.py was needed because llama-cpp-python adds a new line to the final response: `[DONE]^M`.
* allow string in initial_prompt, closes #35Martin Bielik2023-06-253
|
* optional max_tokens, fixes #42Martin Bielik2023-06-111
|
* importing vim module, fixes #43Martin Bielik2023-05-231
|
* print error in debugMartin Bielik2023-05-193
|
* clear echo message after completionMartin Bielik2023-05-143
|
* Allow single undoBonaBeavis2023-05-041
| | | Fixes https://github.com/madox2/vim-ai/issues/14
* http error handlingMartin Bielik2023-04-261
|
* pass config as a parameterMartin Bielik2023-04-222
|
* recover for unfinished chatMartin Bielik2023-04-222
|
* move prompt to pythonMartin Bielik2023-04-211
|
* empty message warning, reference #20Martin Bielik2023-04-181
|
* nvim keyboard interrupt handlingMartin Bielik2023-04-161
|
* improved undo sequence breakMartin Bielik2023-04-151
|
* fixed error handlingMartin Bielik2023-04-151
|
* using messages to show error/warningMartin Bielik2023-04-151
|
* reusing error handlerMartin Bielik2023-04-153
|
* reorganized request optionsMartin Bielik2023-04-153
|
* using scoped variablesMartin Bielik2023-04-152
|
* removing openai-python from docuMartin Bielik2023-04-131
|
* implemented request_timeoutMartin Bielik2023-04-133
|
* poc: removing openai dependencyMartin Bielik2023-04-133
|
* moving import openai check to python scriptsMartin Bielik2023-04-123
|
* fixed debug variable typeMartin Bielik2023-04-111
|
* fixed legacy methodMartin Bielik2023-04-111
|
* added debug loggingMartin Bielik2023-04-113
|
* improved error handlingMartin Bielik2023-04-102
|
* populate options in chatMartin Bielik2023-04-103
|
* parse chat header optionsMartin Bielik2023-04-093
|
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-10 21:35:22 +0000