Carl-Robert Linnupuu
11ea8a4ae9
fix: tool window autoscroller ( closes #459 )
2024-06-30 01:26:09 +03:00
Carl-Robert Linnupuu
572d3626bd
fix: build/compatibility issues
2024-06-21 11:38:29 +03:00
PhilKes
56cdc6d76b
feat: set maxTokens and temperature for Ollama chat and codecompletion
2024-06-21 11:16:57 +03:00
PhilKes
b71cabdca6
feat: optional apiKey field for Ollama service
2024-06-21 11:16:51 +03:00
Carl-Robert Linnupuu
78e4353f91
fix: commit message placeholders
2024-06-21 11:16:43 +03:00
Carl-Robert Linnupuu
1eacb7d432
fix: replace codegpt website base url
2024-06-21 11:16:00 +03:00
Carl-Robert Linnupuu
d92e98ba98
feat: introduce openai and anthropic models for subscribed users
2024-06-06 15:29:36 +03:00
Carl-Robert Linnupuu
4e12034d0d
fix: disable code completions by default
2024-06-06 15:29:31 +03:00
Phil
e96f6a418a
feat: add field for environment variables for Llama server ( #550 )
...
Co-authored-by: Carl-Robert <carlrobertoh@gmail.com>
2024-06-06 15:29:10 +03:00
Phil
4c2f62d66d
fix: remove trailing slashes from URL text fields ( #579 )
2024-06-06 15:29:03 +03:00
Rene Leonhardt
235418e9ac
feat: Support Phi-3 Medium 128K ( #577 )
2024-06-06 15:28:59 +03:00
Rene Leonhardt
1ef8afbc73
feat: Support Stable Code Instruct 3B ( #552 )
...
* feat: Support Stable Code Instruct 3B
* feat: Sort LLaMA models in settings
2024-06-06 15:28:54 +03:00
Carl-Robert Linnupuu
893a125adc
fix: backward compatibility issues on plugin update ( fixes #551 )
2024-05-15 00:13:37 +03:00
Rene Leonhardt
44b61a443a
feat: Show server name in start/stop notifications ( #546 )
...
* feat: Show server name in start/stop notifications
* feat: Show opposite action in notification
* feat: Pre-select biggest downloaded parameter size on model change
* chore: Update to latest llama.cpp fixes (2024-05-14)
2024-05-15 00:13:30 +03:00
Carl-Robert Linnupuu
14eab9d48c
fix: compatibility issue
2024-05-14 00:22:22 +03:00
Carl-Robert Linnupuu
a18b74fe26
feat: add gpt-4o model ( closes #547 )
2024-05-14 00:10:38 +03:00
Carl-Robert Linnupuu
a0b14551c7
fix: landing page hyperlinks
2024-05-13 19:09:38 +03:00
Rene Leonhardt
a26b8f29ff
feat: Start/stop LLaMA Server from statusbar ( #544 )
2024-05-13 19:09:32 +03:00
Carl-Robert Linnupuu
3c8778ae98
refactor: remove llama download marker from toolwindow popup menu
2024-05-13 17:58:35 +03:00
Carl-Robert Linnupuu
b65edd86a0
fix: build
2024-05-13 16:31:24 +03:00
Carl-Robert Linnupuu
1373e96eaa
refactor: remove max_tokens configuration and other minor fixes
2024-05-13 16:04:40 +03:00
Rene Leonhardt
c4b65e7a53
feat: Visualize downloaded models ( #543 )
...
* feat: Visualize downloaded models
* Simplify GeneralSettings access
2024-05-13 16:02:27 +03:00
Carl-Robert Linnupuu
4dbe0f5532
fix: lookup completion request validation
2024-05-13 16:01:49 +03:00
Rene Leonhardt
5440fc7469
fix: Handle problems graciously ( #541 )
2024-05-13 16:01:34 +03:00
Carl-Robert Linnupuu
2e961bcb6a
fix: lookup and commit message completions for codegpt provider
2024-05-13 16:00:05 +03:00
Rene Leonhardt
3f75057b8f
chore: Update to CodeGemma 1.1 7b Instruct ( #534 )
2024-05-13 15:59:50 +03:00
Carl-Robert Linnupuu
52b5bcce96
fix: long-running tasks on EDT when initializing forms
2024-05-13 15:59:42 +03:00
Carl-Robert
4d0166b0ff
feat: extract providers into their standalone configurables ( #538 )
...
* fix: extract services to their own configurables
* feat: switch to selected provider automatically upon apply
* fix: credentials loading at once
* fix: rename llama.cpp title
2024-05-13 15:59:14 +03:00
Carl-Robert
61613336bb
feat: add CodeGPT "native" API provider ( #537 )
...
* feat: support codegpt client
* feat: add basic request handler test
* refactor: minor cleanup
2024-05-13 15:59:04 +03:00
Phil
9677e10d6b
feat: add Google Gemini API support ( #535 )
2024-05-13 15:58:14 +03:00
Phil
143fea57fa
fix: refresh Ollama models only when service is changed to Ollama ( #536 )
2024-05-13 15:57:48 +03:00
Phil
a173840ee5
Revert "fix: use /infill for llama.cpp code-completions ( #513 )" ( #533 )
...
This reverts commit 8de72b3301
2024-05-13 15:57:40 +03:00
Rene Leonhardt
d743b60bfe
feat: Support CodeQwen1.5-Chat model ( #527 )
...
* feat: Support CodeQwen1.5-Chat model
* Declare model directories explicitly
2024-05-13 15:57:13 +03:00
Jack Boswell
5fb6589dc6
feat: Implement Ollama as a high-level service ( #510 )
...
* Initial implementation of Ollama as a service
* Fix model selector in tool window
* Enable image attachment
* Rewrite OllamaSettingsForm in Kt
* Create OllamaInlineCompletionModel and use it for building completion template
* Add support for blocking code completion on models that we don't know support it
* Allow disabling code completion settings
* Disable code completion settings when an unsupported model is entered
* Track FIM template in settings as a derived state
* Update llm-client
* Initial implementation of model combo box
* Add Ollama icon and display models as list
* Make OllamaSettingsState immutable & convert OllamaSettings to Kotlin
* Add refresh models button
* Distinguish between empty/needs refresh/loading
* Avoid storing any model if the combo box is empty
* Fix icon size
* Back to mutable settings
There were some bugs with immutable settings
* Store available models in settings state
* Expose available models in model dropdown
* Add dark icon
* Cleanups for CompletionRequestProvider
* Fix checkstyle issues
* refactor: migrate to SimplePersistentStateComponent
* fix: add code completion stop tokens
* fix: display only one item in the model popup action group
* fix: add back multi model selection
---------
Co-authored-by: Carl-Robert Linnupuu <carlrobertoh@gmail.com>
2024-05-13 15:57:00 +03:00
Phil
7b386686b0
fix: CustomService Test connection with correct settings ( #531 )
2024-05-13 15:55:28 +03:00
Carl-Robert Linnupuu
43ec887b17
fix: build
2024-05-13 15:55:22 +03:00
Phil
b70aad9980
fix: Storing HuggingFaceModel by modelName instead of quantization only ( #529 )
2024-05-13 15:55:17 +03:00
Phil
908d8b9286
feat: add CodeGemma InfillPromptTemplate ( #530 )
2024-05-13 15:55:08 +03:00
Rene Leonhardt
af2391ac9a
feat: Support CodeGemma 7b Instruct model ( #524 ) ( #525 )
2024-05-13 15:55:02 +03:00
Jack Boswell
c37f02b6ad
refactor: Expand and explicitly handle cases where a ServiceType is checked ( #521 )
...
This streamlines changes to ServiceType, where any additions or removals will be flagged at compile time to be handled, instead of silently falling back to a default value.
2024-05-13 15:54:54 +03:00
Rene Leonhardt
f557d02748
feat: Support Phi-3 Mini model ( #516 )
2024-05-13 15:54:06 +03:00
Phil
5cd9531246
fix: focus on new editor action and refresh editor actions on apply ( #518 )
2024-05-13 15:54:00 +03:00
Phil
1842c98084
fix: use /infill for llama.cpp code-completions ( #513 )
2024-05-13 15:53:46 +03:00
Carl-Robert Linnupuu
28aac5a369
fix: commit message generation for custom openai services ( closes #496 )
2024-05-13 15:52:53 +03:00
Rene Leonhardt
10b8535347
fix: NPE when using unsupported model for code completions ( #499 )
2024-05-13 15:52:48 +03:00
Rene Leonhardt
f7ce60e1a4
feat: Add Llama 3 download sizes ( #498 )
2024-05-13 15:52:44 +03:00
Carl-Robert Linnupuu
ff528e91e0
fix: build errors
2024-04-22 00:07:39 +03:00
Carl-Robert Linnupuu
69dc2ea9fc
fix: llama server success callback trigger
2024-04-22 00:00:41 +03:00
Carl-Robert Linnupuu
477d51ce7c
fix: llama3 prompt
2024-04-22 00:00:35 +03:00
Rene Leonhardt
fe06f559b3
feat: Support Llama 3 model ( #479 )
...
* feat: Support Llama 3 model (#478 )
* Use new InfillPrompt
* Switch to lmstudio-community
* Use new Prompt
* llama.cpp removed the BOS token
https://github.com/ggerganov/llama.cpp/pull/6751/commits/a55d8a9348fc9e9215229bf03f96ecff4dcc7c91
* Add tests
* I would prefer a stream based solution
* Add 70B models
* Add tests for skipping blank system prompt
* Remove InfillPrompt for now
2024-04-21 23:47:55 +03:00
