Commit graph

26 commits

Author SHA1 Message Date
Georgi Gerganov
f610bd28e7
readme : add Qwen3 30B 2025-11-01 18:49:10 +02:00
igardev
08c0a22a73
Agent entity added (#97)
- Agent entity added - agents with different system prompts and default tools could be selected
- Fixed showing tables in llama agent
- Local envs with gpt-oss 20B added (also available for import from here )
2025-08-18 10:48:55 +03:00
igardev
8e0531f906
Add models from huggingface (#89)
* Adding a model from huggingface implemented

* Tool llama_vscode_help is added
2025-08-11 17:40:11 +03:00
igardev
e49bb9f128
Agent support added (#79)
- Llama Agent UI in Explorer view
- OpenRouter API model selection (assumes your OpenRauter key is in setting Api_key_tools)
- MCP Support
- 9 internal tools available for use
- custom_tool - returns the content of a file or a web page
- custom_eval_tool - write your own tool in Typescript/javascript
- Attach the selection to the context
- Configure maximum loops for Llama Agent
2025-08-01 15:59:16 +03:00
Georgi Gerganov
7f889bba32
readme : add windows install command (#71) 2025-05-22 20:41:04 +03:00
Daniel Bevenius
3126abfeb5
readme : update llama-server commands with fim presets (#34) 2025-02-20 09:24:30 +02:00
Georgi Gerganov
5fd34bf605
readme : add example 2025-02-03 09:14:43 +02:00
Georgi Gerganov
b72b9c260b
readme : add CPU-only configs 2025-01-31 12:41:21 +02:00
Georgi Gerganov
01cf5c8366
readme : add Open VSX link 2025-01-29 15:28:12 +02:00
Georgi Gerganov
9e4503ee21
readme : minor simplifications of the server commands 2025-01-27 09:45:41 +02:00
Georgi Gerganov
4316fffd89
readme : remove tip 2025-01-26 16:52:18 +02:00
Georgi Gerganov
62dba7b842
readme : add tip 2025-01-26 14:31:21 +02:00
Georgi Gerganov
fa1d157a6d
readme : fix wording about auto-suggest 2025-01-23 14:40:33 +02:00
Georgi Gerganov
b264d5d0a2
readme : add llama.vim 2025-01-22 19:49:35 +02:00
Georgi Gerganov
57f7f382b6
readme : add GIF 2025-01-22 18:51:25 +02:00
Georgi Gerganov
b789ffb577
readme : update extension link 2025-01-21 22:43:57 +02:00
Georgi Gerganov
63c5323d42
readme : add info about model location 2025-01-21 15:27:58 +02:00
Radoslav Gerganov
1c1d020c10
Add direct install link with vscode scheme (#3) 2025-01-21 14:44:34 +02:00
Georgi Gerganov
aad0a87632
readme : minor 2025-01-21 14:33:16 +02:00
Georgi Gerganov
7c7963fc40
readme : add extension instructions 2025-01-21 14:26:51 +02:00
Georgi Gerganov
8c2de3a57e
readme : update acknowledgements 2025-01-21 14:15:10 +02:00
Georgi Gerganov
1e5649b03f
readme : add wiki link 2025-01-21 14:12:25 +02:00
Georgi Gerganov
8019f5729d
readme : add images 2025-01-21 14:09:40 +02:00
igardev
cc07186197
First version of llama.vscode extension (#2)
* First draft version of llama.vscode plugin

* Update the instructions how to run llama.cpp server on Mac in Readme file. Removed not needed imports and not used variables.

* Fix the problem with not sending extra context.

* Reduce the number of requests on fast typing or deleting. Fix error on suggestion when curson on last line.

* Reduce last completion if the typed chars are the first chars of it

* Small fixes and improvements
- Next word in case of end of line should be the first word of the next line
- Similar for next line
- Avoid sendind requests on accepting next word or next line.

* Fix the problem with wrong prompt sending on removing chars with backspace.
No cashing if the suggestion is empty.
nindent parameter added in the request to llama-server

* Revert the publisher name change as it results in error on creating the installation file

* -ctrl+shift+l forces trigerring a request (no cache)
- Status message improved
- other minor fixes

* - n_indent added in the request to llama server
- ctrl+alt+c - copy chunks in the clipboard

* - n_indent parameter is now correctly sent to llama server
- Search in cache extended - now searches for match, which partially or completly includes prompt
- Messages in the status bar are now short (for users, not for developers)
- Setting for choosing language for the status bar messages is added.

* - n_indent parameter is now correctly sent to llama server
- Search in cache extended - now searches for match, which partially or completly includes prompt
- Messages in the status bar are now short (for users, not for developers)
- Setting for choosing language for the status bar messages is added.

* Readme file updated and other small refactorings.

* Run async slow pick chunks operations

* Fix error on search in cache.
Don't send a request if one is still running.

* Fix error on ignoring the result of the last request in some situations.

* Change the key assignment:
Copy chunks and cache: Ctrl+Shift+,
Accept next word: Ctrl+right arrow

* - Improve the time calculation for status bar
- Show additional info only if show_info is true. Show basic info (thinkg..., no suggestion + time) always

* Fix the error on accepting a line when the cursor is at the last line.

* Minor whitespace clean-up

* More whitespaces

* Update readme

---------

Co-authored-by: igardev <ivailo.gardev@akros.ch>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-01-21 14:05:38 +02:00
Georgi Gerganov
9aaa132074
readme : add draft implementation 2025-01-08 16:24:46 +02:00
Georgi Gerganov
6e2ac7b693
init 2025-01-08 15:23:06 +02:00