summaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFiles
* Update README.mdChris Stryczynski2024-02-171
| | | Fix instructions which lead to `Undefined variable: g:vim_ai_chat` if config options are not initially set
* Merge pull request #74 from jkoelker/includeMartin Bielik2024-01-255
|\ | | | | feat(chat): add `include` role to include files
| * feat(chat): add `include` role to include filesJason Kölker2024-01-245
|/ | | | | | | | | | | | | | | | | | | | | | | | | 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 Bielik2023-12-022
|
* Merge pull request #64 from cposture/fix-visual-selectionMartin Bielik2023-12-024
|\ | | | | fix selection include extra content when the user is in visual mode
| * fix selection include extra content when the user is in visual modecposture2023-12-024
|/
* fixed python3.12 slash escaping, fixes #61Martin Bielik2023-11-011
|
* Merge pull request #59 from madox2/base-url-configMartin Bielik2023-10-216
|\ | | | | Custom APIs, closes #55, closes #51
| * removed unused importMartin Bielik2023-10-212
| |
| * Merge remote-tracking branch 'origin/main' into base-url-configMartin Bielik2023-10-214
| |\ | |/ |/|
* | use gpt-3.5-turbo-instruct by default, closes #48Martin Bielik2023-09-263
| |
* | compact org id docuMartin Bielik2023-09-181
| |
* | Merge pull request #54 from duylam/openai-org-supportMartin Bielik2023-09-182
|\ \ | | | | | | Support including OpenAI Org ID in the request to OpenAI API endpoints
| * | Include OpenAI Org ID from the token configDuy Lam2023-09-092
|/ /
| * docu on custom apisMartin Bielik2023-10-211
| |
| * endpoint_url configMartin Bielik2023-10-215
| |
| * option to disable authorizationMartin Bielik2023-10-214
| |
| * base_url extracted to config, docuMartin Bielik2023-10-215
| |
| * 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 Bielik2023-06-254
|
* optional max_tokens, fixes #42Martin Bielik2023-06-112
|
* selection boundary issue reference, fixes #45Martin Bielik2023-05-301
|
* importing vim module, fixes #43Martin Bielik2023-05-231
|
* tags updateMartin Bielik2023-05-221
|
* print error in debugMartin Bielik2023-05-193
|
* Merge pull request #38 from madox2/nextMartin Bielik2023-05-143
|\ | | | | clear echo message after completion, fixes #16
| * clear echo message after completionMartin Bielik2023-05-143
|/
* Added command example, fixes #37Martin Bielik2023-05-111
|
* Merge pull request #34 from KupferDigital/mainMartin Bielik2023-05-081
|\ | | | | Allow modification of vim_ai_open_chat_presets
| * Allow modification of vim_ai_open_chat_presetsBonaBeavis2023-05-071
|/
* Merge pull request #30 from BonaBeavis/patch-1Martin Bielik2023-05-051
|\ | | | | Allow single undo
| * Allow single undoBonaBeavis2023-05-041
|/ | | Fixes https://github.com/madox2/vim-ai/issues/14
* configurable paste modeMartin Bielik2023-05-024
|
* using value from extended configMartin Bielik2023-05-021
|
* http error handlingMartin Bielik2023-04-261
|
* wiki referencesMartin Bielik2023-04-241
|
* split to AI commands and utilitiesMartin Bielik2023-04-231
|
* renamed custom commands examplesMartin Bielik2023-04-231
|
* added AINewChat commandMartin Bielik2023-04-224
|
* open_chat_command presetsMartin Bielik2023-04-224
|
* custom commands documentationMartin Bielik2023-04-223
|
* pass config as a parameterMartin Bielik2023-04-225
|
* fixed redo in chatMartin Bielik2023-04-221
|
* fixed redo in chatMartin Bielik2023-04-221
|
* recover for unfinished chatMartin Bielik2023-04-222
|
* Merge branch 'main' into nextMartin Bielik2023-04-211
|\
| * docu typo fixMartin Bielik2023-04-211
| |
* | move prompt to pythonMartin Bielik2023-04-212
| |
* | reuse chat if it is active in current tabMartin Bielik2023-04-211
|/
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-10 14:29:50 +0000