endpoints : add experimental OpenAI support (#16)

* initial openai compatible api endpoint integration

* fix watch

* added openAiClientModel to config; tested with local vllm server

* fixed config and completions to work with FIM models by default

* remove unnecessary try catch

* core : remove repeating suffix of a suggestion + fix speculative FIM (#18)

* Remove repeating suffix of a suggestion

* If linesuffix is empty - cut the repeating suffix of the suggestion.

* If there is a linesuffix, suggest only one line, don't make hidden second request

* Fix the caching of the future suggestion in case of max inputPrefix length.

---------

Co-authored-by: igardev <[email protected]>

* core : disable trimming of suggestions

* release : v0.0.6

* readme : add CPU-only configs

* fixed configuration/settings UI

* fixed conflicts

* fix watch

* fixed

* fixes

* update version

* readme : add example

* core : fix cutting the lines of a suggestion (#22)

* Fix the problem with cutting the lines of a suggestion after the first one.

* Remove the less important checks on cutting the suggestion.

---------

Co-authored-by: igardev <[email protected]>

* Fix manual trigger without cache + accept always on pressing a Tab (#25)

* Ensure Ctrl+Shift+L always makes a new request to the servers.

* If a suggestion is visible - pressing a Tab always accepts it.

---------

Co-authored-by: igardev <[email protected]>

* fixed conflicts

* fix watch

* fixed

* fixes

* initial openai compatible api endpoint integration

* added openAiClientModel to config; tested with local vllm server

* fixed config and completions to work with FIM models by default

* fixed

* make api key optional for openai compatible endpoints as well

* updated to work with llama.cpp without api key

* removed this.handleOpenAICompletion() call from prepareLlamaForNextCompletion per @igardev

* updated package-lock.json after build

---------

Co-authored-by: igardev <[email protected]>
Co-authored-by: igardev <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>

Author: 4 people

.prettierrc

@@ -0,0 +1,5 @@
+{
+    "printWidth": 140,
+    "tabWidth": 4,
+    "useTabs": false
+}

.vscode/settings.json

@@ -1,11 +1,11 @@
 // Place your settings in this file to overwrite default and user settings.
 {
-	"files.exclude": {
-		"out": false // set this to true to hide the "out" folder with the compiled JS files
-	},
-	"search.exclude": {
-		"out": true // set this to false to include "out" folder in search results
-	},
-	// Turn off tsc task auto detection since we have the necessary tasks as npm scripts
-	"typescript.tsc.autoDetect": "off"
+    "files.exclude": {
+        "out": false // set this to true to hide the "out" folder with the compiled JS files
+    },
+    "search.exclude": {
+        "out": true // set this to false to include "out" folder in search results
+    },
+    // Turn off tsc task auto detection since we have the necessary tasks as npm scripts
+    "typescript.tsc.autoDetect": "off"
 }

package-lock.json

@@ -114,10 +114,25 @@
           "default": true,
           "description": "If code completion should be trggered automatically (true) or only by pressing Ctrl+l."
         },
-        "llama-vscode.api_key": {
+       "llama-vscode.api_key": {
           "type": "string",
           "default": "",
-          "description": "llama.cpp server api key (optional)"
+          "description": "llama.cpp server api key or OpenAI endpoint API key (optional)"
+        },
+        "llama-vscode.is_openai_compatible": {
+          "type": "boolean",
+          "default": false,
+          "description": "If the server exposes an OpenAI API compatible endpoint."
+        },
+        "llama-vscode.openai_client_model": {
+          "type": "string",
+          "default": "",
+          "description": "The FIM friendly model supported by your OpenAI compatible endpoint to be used (e.g., Qwen2.5-Coder-14B-4-bit)"
+        },
+        "llama-vscode.openai_prompt_template": {
+          "type": "string",
+          "default": "<|fim_prefix|>{inputPrefix}{prompt}<|fim_suffix|>{inputSuffix}<|fim_middle|>",
+          "description": "The prompt template to be used for the OpenAI compatible endpoint."
         },
         "llama-vscode.n_prefix": {
           "type": "number",
@@ -203,8 +218,12 @@
         }
     }
   },
+  "scripts": {
+    "watch": "tsc -watch -p ./"
+  },
   "dependencies": {
-    "axios": "^1.1.2"
+    "axios": "^1.1.2",
+    "openai": "^4.80.1"
   },
   "devDependencies": {
     "@types/jest": "^29.5.14",