vrr/ProxyAI
2
0
Fork 0
mirror of https://github.com/carlrobertoh/ProxyAI.git synced 2026-05-12 05:51:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

#178 - Add support for running local LLMs via LLaMA C/C++ port (#249)

Browse source 
* Initial implementation of integrating llama.cpp to run LLaMA models locally

* Move submodule

* Copy llama submodule to bundle

* Support for downloading models from IDE

* Code cleanup

* Store port field

* Replace service selection radio group with dropdown

* Add quantization support + other fixes

* Add option to override host

* Fix override host handler

* Disable port field when override host enabled

* Design updates

* Fix llama settings configuration, design changes, clean up code

* Improve You.com coupon design

* Add new Phind model and help tooltip

* Fetch you.com subscription

* Add CodeBooga model, fix downloadable model selection

* Chat history support

* Code refactoring, minor bug fixes

* UI updates, several bug fixes, removed code llama python model

* Code cleanup, enable llama port only on macOS

* Change downloaded gguf models path

* Move some of the labels to codegpt bundle

* Minor fixes

* Remove ToRA model, add help texts

* Fix test

* Modify description
This commit is contained in:
Carl-Robert 2023-11-03 12:00:24 +02:00 • committed by GitHub
parent ca2eb9b6fa
commit 45908e69df
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
71 changed files with 2748 additions and 533 deletions
Download patch file Download diff file Expand all files Collapse all files

20
src/main/java/ee/carlrobert/codegpt/completions/CompletionClientProvider.java
View file

@ -5,11 +5,14 @@ import ee.carlrobert.codegpt.credentials.AzureCredentialsManager;
import ee.carlrobert.codegpt.credentials.OpenAICredentialsManager;
import ee.carlrobert.codegpt.settings.advanced.AdvancedSettingsState;
import ee.carlrobert.codegpt.settings.state.AzureSettingsState;
import ee.carlrobert.codegpt.settings.state.LlamaSettingsState;
import ee.carlrobert.codegpt.settings.state.OpenAISettingsState;
import ee.carlrobert.codegpt.settings.state.YouSettingsState;
import ee.carlrobert.llm.client.Client;
import ee.carlrobert.llm.client.ProxyAuthenticator;
import ee.carlrobert.llm.client.azure.AzureClient;
import ee.carlrobert.llm.client.azure.AzureCompletionRequestParams;
import ee.carlrobert.llm.client.llama.LlamaClient;
import ee.carlrobert.llm.client.openai.OpenAIClient;
import ee.carlrobert.llm.client.you.UTMParameters;
import ee.carlrobert.llm.client.you.YouClient;
@ -33,8 +36,16 @@ public class CompletionClientProvider {
utmParameters.setMedium("jetbrains");
utmParameters.setCampaign(CodeGPTPlugin.getVersion());
utmParameters.setContent("CodeGPT");
return new YouClient.Builder(sessionId, accessToken)
// FIXME
return (YouClient) new YouClient.Builder(sessionId, accessToken)
.setUTMParameters(utmParameters)
.setHost(YouSettingsState.getInstance().getBaseHost())
.build();
}
public static LlamaClient getLlamaClient() {
return new LlamaClient.Builder()
.setPort(LlamaSettingsState.getInstance().getServerPort())
.build();
}
@ -65,10 +76,9 @@ public class CompletionClientProvider {
builder.setProxy(
new Proxy(advancedSettings.getProxyType(), new InetSocketAddress(proxyHost, proxyPort)));
if (advancedSettings.isProxyAuthSelected()) {
builder.setProxyAuthenticator(
new ProxyAuthenticator(
advancedSettings.getProxyUsername(),
advancedSettings.getProxyPassword()));
builder.setProxyAuthenticator(new ProxyAuthenticator(
advancedSettings.getProxyUsername(),
advancedSettings.getProxyPassword()));
}
}