Preview (#1393)

* Nate/autocomplete-metrics (#1230) * ⚡️ use context.selectedCompletionInfo, deduplicate logs * ⚡️ don't reject if user keeps typing same as completion * ⚡️ vscode autocomplete edge cases * 🚧 WIP on vscode autocomplete * ⚡️ better bracket handlng * ⚡️ improved multi-line detection * Active file default context (#1231) * 🚸 include currently active file by default * 🚸 warn if non-autocomplete model being used * ✨ try hole filling template for gpt * 💄 ui for no context * ⚡️ leave out bottom of excessively large files * 🎨 finish listDir * 🚧 gui fixes * 🏷️ update IMessenger.on return type * 🐛 fix jetbrains types + IDE detection * 🧑‍💻 set up debugging for binary with TcpMessenger * 👷 fix prepackage.js * 🧑‍💻 turn off debug mode for intellij * 🐛 merge fixes * 🐛 fixes after refactor * 🚧 experimenting with perplexity style streaming * 🐛 fix #1237 * 💚 fix type error * ⚡️ improve LSP usage in autocomplete * 🐛 fix content parsing regression in /edit * add PySide6 docs to preindexed docs (#1236) * CON-232 bring custom docs to top, alphabetize doc results, make scrol… (#1239) * CON-232 bring custom docs to top, alphabetize doc results, make scrollable * CON-232 cleanup --------- Co-authored-by: Justin Milner <jmilner@jmilner-lt2.deka.local> * CON-1067 condense some things * 🚚 [Auxiliary -> Continue] Sidebar * 🔊 log completion options in ~/.continue/sessions * CON-1067 wrong ret val fix * CON-1067: fixes from testing * ⚡️ filter out completions that are only punctuation/space * ⚡️ inject intellisense docs, no multi-line on comments * ⚡️ crawl type definitions for autocomplete * ⚡️ truncate function text * ⚡️ cache LSP calls * ⚡️ find recently edited ranges with perfect prefix match * 🐛 fix gif paths * ⚡️ bring back double new line stop words * 📌 add yarn lock files * 🐛 allow language keywords to be generated * 💄 toggle on help button * 🎨 defaultContext option * 🐛 fix lancedb bug by upgrading * 🐛 fix groq stop tokens * 🐛 preventDefault to avoid double paste * 🚸 don't repeatedly override cmd+J * 🧑‍💻 fix npm run test in core * 📝 change description * 🐛 silence Ollama invalid server state warning * ⚡️ more accurate getTerminalContents * ⚡️ make getTerminalContents more accurate * 🧑‍💻 use yarn instead of npm * 👷 fix yarn add --no-save in prepackge * 🐛 correctly read entire notebook file contents * ➕ import handlebars * 🔥 remove unnecessary migrations * ⚡️ improve /comment prompt * Add debug terminal context menu (#1261) * Add --no-dependencies to vsce package (#1255) This is not needed because we bundle first with esbuild, and vsce pack has issues with modern package managers. see: microsoft/vscode-vsce#421 (comment) * ui: change line decoration color to use vscode theme (#1253) * ui: change line decoration color to use vscode theme to give user a more consistent experience by letting the decoration color to user the color defined in the theme. * fix: incorrect color item should be line background not text background because the decoration is for the whole line * 🎨 refactor indexing state into a single object * CON-223 Correct diff streaming abort (#1263) Co-authored-by: Justin Milner <jmilner@jmilner-lt2.deka.local> * 📦 switch to pnpm (#1265) * 🎨 use pnpm instead of yarn * ➕ make dependencies explicit for pnpm * 🐛 add powershell to extension mapping, and default to ext * Add stream support for Bedrock Anthropic * 🎨 make llamatokenizer commonjs compatible * ➕ add esbuild optional deps * 🚚 rename vendor/node_modules -> modules * 🔖 update core version * 🐛 fixes for transformers.js compatibility * 🔖 update core version * 🎨 set modelPath in constructor * 🎨 fix transformers.js import * 🎨 eslint enforce import extensions * 🎨 require -> import * 🚸 notify user if not diff in /commit * 💄 Improve colors of the IntelliJ tool window icon (#1273) Without this fix, the continue icon sticks out from the other toolwindow icons, resulting in an inconsistent appearance of the whole IDE and creates a feeling that the continue plugin "doesn't fit, something must be broken". According to https://plugins.jetbrains.com/docs/intellij/icons.html#new-ui-icon-colors specific colors are needed to work nicely with dark and light modes. Bonus is that the active tool window icon color then changes automatically to white. Co-authored-by: Lukas Baron <LukasBaron@gmail.com> * ✨ send Bearer token to Ollama if apiKey set * 🐛 fix slash command bug * 🧑‍💻 add onnxruntime (--save-dev) for types * 🐛 don't apply to file when running code block in terminal * 🐛 avoid double paste * ✨ gpt-4o * 🎨 pass uniqueId to constructor * 🚸 focus without scrolling into vie * 🎨 refactoring for continue-proxy LLM (#1277) * 🐛 continue server client fixes * 🎨 refactor OpenAI _getHeaders * 🎨 pass ideSettings to llmFromDescription * ⚡️ improve add docstring command * 💚 ci updates * 🐛 merge fixes * 💄 increase font size in JB * 🐛 fix repeated paste bug * 🐛 fix build script * 🩹 various small improvements * 📌 pin esbuild 0.17.19 * 🧑‍💻 pnpm i gui in prepackage * 🐛 show all diff changes in vscode * 🩹 getMetaKeyName * 🐛 fix reading of unopened ipynb files * ⚡️ gpt-4o system prompt * 💄 make font size configurable in config.json ui.fontSize * 🩹 properly dispose of diff handler * 🐛 fix indexing status display * ⚡️ context pruning * 🎨 update free trial models * fix: remove some backup files generated by pkg if present (#1287) * adjust toCopy (#1305) Co-authored-by: Justin Milner <jmilner@jmilner-lt2.deka.local> * Nate/prompt-file (#1308) * ✨ .prompt files * 🧑‍💻 back to npm : ( * 🎨 nicer dropdown icon * 🎨 full switch back to npm * 🧑‍💻 uninstall script for fresh start * 🎨 updated package-locks * 🔥 remove hello from continuerc.json * 🔥 remove example files * 🎨 update test prompt * 🎨 update prompt * 🎨 update test prompt * 👷 create out/node_modules in prepackage.js * Log prompt-tokens to devdb and show in 'My Usage' view (#1309) * Also log the number of prompt tokens to the dev-db * Show prompt tokens in 'My Usage' view * 🔥 remove console logs * add lm studio tab-autocomplete walkthrough (#1298) * 📝 update autocomplete LM Studio docs * 💚 fix prepackage.js * ⬆️ upgrade lancedb version * 🚸 make it easier to continue past trial * 🚸 improve model setup process * 📌 update package-lock.jsons * 🔀 merge changes * 🩹 small fixes * 🐛 fix jetbrains build * 🩹 more jetbrains fixes * 🎨 jetbrains improvements * 🐛 fix lancedb prob in jetbrains build * 👷 update jetbrains build process * ✨ intellij problems context provider * 👷 add script utils file * 💚 fix jetbrains build regression * 🎨 dynamic import transformers.js * 🩹 small jetbrains updates * ✨ folder context provider in jetbrains * 🎨 many more jetbrains improvements * 🐛 fix prompt file loading bug * docs: add setup guide for OpenRouter (#1284) * Update preIndexedDocs.ts (#1292) Add Bootstrap and Alpine.js as pre indexed docs. * add toString (#1324) * add toString * Fix indentation --------- Co-authored-by: Justin Milner <jmilner@jmilner-lt2.deka.local> * don't overwrite all models in onboarding * 🔧 override headers with custom headers * ✨ allow overwriting slash command description * feature flag (#1327) * ➕ feature flags dependency * 🎨 make getHeaders awaitable * 🔒️ token count for abuse monitoring * 👷 remove win32-arm64 target * Update build.js (#1330) Fix error: EBUSY: resource busy or locked, rmdir '...\continue\binary\tmp\continue-node_modules-lancedb' * 📌 pin onnxruntime version to match transformers.js * 🎨 transformers cleanup, extensionVersion header * 🔥 remove lingering pnpm * 🎨 update default models * 🎨 update defaults * 👷 fix version in build post-check * 🎨 test.js in dev * 🧑‍💻 cleaning * Add Gemini 1.5 Flash as a model (#1337) * 🎨 log dev data for tokens generated * Expose custom context provider registration through a vscode extension api. (#1288) * 🔀 merge fixes * ⚡️ small improvements * 🎨 tell users transformers.js not supported * 🎨 trial updates * 📝 update jetbrains readmej * ⚡️ Use gptEditPrompt for Mistral * ✨ Codestral FIM * 🔖 update gradle version * Fix typo "Experimantal" (#1353) * 🎨 Refactor core (#1281) * 🎨 refactor out react context * 🎨 refactor local storage * 🎨 refactor IdeMessenger * 🔥 removing unused files * 🚚 move scripts * ✅ setup VSCode integration testing * 🎨 fix test-related stuff * 🚧 testing * 🎨 tweak terminal cmd+L * 🧑‍💻 install biome in core * 🎨 run biome check on core * 🎨 run biome check in vscode * 🎨 run biome check in binary * 🧑‍💻 global biome config * 🎨 run biome check on core * 🎨 run biome check in vscode * 🎨 fix a few biome warnings * 🚧 WIP on protocols * 🚧 progress, organizing, about to remove webviewCore protocol * 🚧 now running * 🚧 move indexing code to core * 🚧 WIP on JetBrains indexing implementation * 🎨 finish listDir * 🚧 gui fixes * 🏷️ update IMessenger.on return type * 🐛 fix jetbrains types + IDE detection * 🧑‍💻 set up debugging for binary with TcpMessenger * 👷 fix prepackage.js * 🧑‍💻 turn off debug mode for intellij * 🐛 merge fixes * 🐛 fixes after refactor * 🐛 merge fixes * 💄 increase font size in JB * 🔀 merge changes * 🩹 small fixes * 🐛 fix jetbrains build * 🩹 more jetbrains fixes * 🎨 jetbrains improvements * 🐛 fix lancedb prob in jetbrains build * 👷 update jetbrains build process * ✨ intellij problems context provider * 👷 add script utils file * 💚 fix jetbrains build regression * 🎨 dynamic import transformers.js * 🩹 small jetbrains updates * ✨ folder context provider in jetbrains * 🎨 many more jetbrains improvements * 🔀 merge fixes * ⚡️ small improvements * 🎨 tell users transformers.js not supported * 🎨 trial updates * 📝 update jetbrains readmej * ⚡️ only use smaller context for local autocomplete models * ⚡️ improve bracket filter * ✨ global .continue/.prompts folder * 💄 improved model setup process * 🥅 display VSCode req errs * ⚡️ improved autocomplete stopping * 🎨 count cmd+I * 🔥 remove duplicate import * 🔥 remove unnecessary headers * ⚡️ limit input history length * ⚡️ limit submenu items until you can use disk-based search, to avoid high memory use * 🔥 remove duplicate function def * Free Trial Auth (#1367) * 🎨 pass gh auth token to free trial * 💄 improved onboarding flow * 🎨 make fewer auth reqs * 🎨 refactor ordering of vscode deps * 🐛 resolve confighandler * ⚡️ autocomplete stopping improvements * 🔥 remove unused auth code * ⚡️ consider previous completion in bracket matching * Build fixes: Remove duplicated code, re-add overwritten commit (#1358) * readd overwritten commit * Remove duplicated code * 📝 update keywords * ✨ /commit slash command * 🎨 make transformers.js esm compatible * ⚡️ fix jetbrains indexing perfomance issue * 💄 autocomplete model onboarding * ✨ mistral free trial autocomplete * ✨ mistral description * 🩹 comment out fireworks.png * 🎨 trial fim model * 🎨 get gh token for autocomplete model trial * ✨ gh auth token jb * 🔧 update config files * 🎨 jetbrains onboarding * 🧑‍💻 create gui/dist if it doesn't exist * Fix sidebar indexing status timing-related bugs (#1368) * readd overwritten commit * Remove duplicated code * Fix status load in and failed state update * Late sidebar open bugs fixed * Change ideMessenger post parameters * debug pause * Don't use global, fix table creation bug * Creating new branch for config-related issues here * cleanup * 🚸 help user avoid login prompt if unwanted * 🚸 update onboarding flow * 📝 codestral as recommended in docs * feat: Add cloudflare as provider * 📝 set up codestral walkthrough * codestral api base * update codestral api link * codestral api link * bearer token * 🐛 fix config loading * cleaner error message * fix codestral templating * 🔥 remove unused kotlin test * 🧑‍💻 ./gradlew build * codestral fim template --------- Co-authored-by: 5eqn <491100866@qq.com> Co-authored-by: Pixel <54180211+pixelsortr@users.noreply.github.com> Co-authored-by: Justin Milner <42585006+justinmilner1@users.noreply.github.com> Co-authored-by: Justin Milner <jmilner@jmilner-lt2.deka.local> Co-authored-by: Devin Gould <djgould0628@gmail.com> Co-authored-by: Dipta Mahardhika <146386738+d-mahard@users.noreply.github.com> Co-authored-by: Ruben Kostandyan <kostard@amazon.com> Co-authored-by: tnglemongrass <113173292+tnglemongrass@users.noreply.github.com> Co-authored-by: Lukas Baron <LukasBaron@gmail.com> Co-authored-by: Fernando <fernando.sanchez.jr@gmail.com> Co-authored-by: Tijs Zwinkels <tijs@tinkertank.eu> Co-authored-by: DJ Johnson <mr.demarcus.johnson@gmail.com> Co-authored-by: sam <1211977+sambarnes@users.noreply.github.com> Co-authored-by: Jose Vega <bloguea.y.gana@gmail.com> Co-authored-by: Pratik Parmar <steveparmar6nov2011@gmail.com> Co-authored-by: Sam El-Husseini <sam.elhusseini@gmail.com> Co-authored-by: Peter Zaback <pzaback@gmail.com> Co-authored-by: James Delorey <jdelorey@cloudflare.com>
continuedev · May 30, 2024 · eba3aba · eba3aba
1 parent 0746bbc
commit eba3aba
Show file tree

Hide file tree

Showing 15 changed files with 498 additions and 381 deletions.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -97,7 +97,7 @@ Pre-requisite: You should use the Intellij IDE, which can be downloaded [here](h
 2. Run `scripts/install-dependencies.sh` or `scripts/install-dependencies.ps1` on Windows. This will install and build all of the necessary dependencies.
 3. To test the plugin, select the "Run Plugin" Gradle configuration and click the "Run" or "Debug" button as shown in this screenshot:
    ![img](./media/IntelliJRunPluginScreenshot.png)
-4. To package the extension, choose the "Build Plugin" Gradle configuration. This will generate a .zip file in `extensions/intellij/build/distributions` with the version defined in `extensions/intellij/gradle.properties`.
+4. To package the extension, run `./gradlew build` (or `./gradlew.bat build` on Windows) from the `extensions/intellij` directory. This will generate a .zip file in `extensions/intellij/build/distributions` with the version defined in `extensions/intellij/gradle.properties`.
 5. If you make changes, you may need to re-build before running the "Build Plugin" configuration
 
    a. If you change code from the `core` or `binary` directories, make sure to run `npm run build` from the `binary` directory to create a new binary.

diff --git a/core/autocomplete/templates.ts b/core/autocomplete/templates.ts
@@ -24,6 +24,13 @@ const stableCodeFimTemplate: AutocompleteTemplate = {
   },
 };
 
+const codestralFimTemplate: AutocompleteTemplate = {
+  template: "<s>[SUFFIX]{{{suffix}}}[PREFIX]{{{prefix}}}",
+  completionOptions: {
+    stop: ["[PREFIX]", "[SUFFIX]"],
+  },
+};
+
 const codegemmaFimTemplate: AutocompleteTemplate = {
   template:
     "<|fim_prefix|>{{{prefix}}}<|fim_suffix|>{{{suffix}}}<|fim_middle|>",
@@ -227,6 +234,10 @@ export function getTemplateForModel(model: string): AutocompleteTemplate {
     return stableCodeFimTemplate;
   }
 
+  if (lowerCaseModel.includes("codestral")) {
+    return codestralFimTemplate;
+  }
+
   if (lowerCaseModel.includes("codegemma")) {
     return codegemmaFimTemplate;
   }

diff --git a/core/index.d.ts b/core/index.d.ts
@@ -304,6 +304,9 @@ export interface LLMOptions {
 
   useLegacyCompletionsEndpoint?: boolean;
 
+  // Cloudflare options
+  accountId?: string;
+
   // Azure options
   engine?: string;
   apiVersion?: string;
@@ -539,7 +542,8 @@ type ModelProvider =
   | "groq"
   | "continue-proxy"
   | "fireworks"
-  | "custom";
+  | "custom"
+  | "cloudflare";
 
 export type ModelName =
   | "AUTODETECT"

diff --git a/core/llm/index.ts b/core/llm/index.ts
@@ -99,6 +99,7 @@ export abstract class BaseLLM implements ILLM {
   apiType?: string;
   region?: string;
   projectId?: string;
+  accountId?: string;
 
   private _llmOptions: LLMOptions;
 
@@ -150,6 +151,7 @@ export abstract class BaseLLM implements ILLM {
     if (this.apiBase && !this.apiBase.endsWith("/")) {
       this.apiBase = `${this.apiBase}/`;
     }
+    this.accountId = options.accountId;
 
     this.engine = options.engine;
     this.apiVersion = options.apiVersion;

diff --git a/core/llm/llms/Cloudflare.ts b/core/llm/llms/Cloudflare.ts
@@ -0,0 +1,62 @@
+import { BaseLLM } from "../index.js";
+import { ChatMessage, CompletionOptions, ModelProvider } from "../../index.js";
+import { stripImages } from "../countTokens.js";
+import { streamSse } from "../stream.js";
+
+export default class Cloudflare extends BaseLLM {
+  static providerName: ModelProvider = "cloudflare";
+
+  private _convertArgs(options: CompletionOptions) {
+    const finalOptions = {
+      max_tokens: options.maxTokens,
+    };
+
+    return finalOptions;
+  }
+
+  protected async *_streamChat(
+    messages: ChatMessage[],
+    options: CompletionOptions,
+  ): AsyncGenerator<ChatMessage, any, unknown> {
+    const headers = {
+      "Content-Type": "application/json",
+      Authorization: `Bearer ${this.apiKey}`,
+      ...this.requestOptions?.headers,
+    };
+
+    const resp = await this.fetch(
+      new URL(
+        `https://api.cloudflare.com/client/v4/accounts/${this.accountId}/ai/v1/chat/completions`,
+      ),
+      {
+        method: "POST",
+        headers,
+        body: JSON.stringify({
+          messages,
+          stream: true,
+          model: this.model,
+          ...this._convertArgs(options),
+        }),
+      },
+    );
+
+    for await (const value of streamSse(resp)) {
+      console.log(value);
+      if (value.choices?.[0]?.delta?.content) {
+        yield value.choices[0].delta;
+      }
+    }
+  }
+
+  protected async *_streamComplete(
+    prompt: string,
+    options: CompletionOptions,
+  ): AsyncGenerator<string> {
+    for await (const chunk of this._streamChat(
+      [{ role: "user", content: prompt }],
+      options,
+    )) {
+      yield stripImages(chunk.content);
+    }
+  }
+}
diff --git a/core/llm/llms/index.ts b/core/llm/llms/index.ts
@@ -29,6 +29,7 @@ import Replicate from "./Replicate.js";
 import TextGenWebUI from "./TextGenWebUI.js";
 import Together from "./Together.js";
 import ContinueProxy from "./stubs/ContinueProxy.js";
+import Cloudflare from "./Cloudflare";
 
 function convertToLetter(num: number): string {
   let result = "";
@@ -99,6 +100,7 @@ const LLMs = [
   Groq,
   Fireworks,
   ContinueProxy,
+  Cloudflare,
 ];
 
 export async function llmFromDescription(

diff --git a/docs/docs/reference/Model Providers/cloudflare.md b/docs/docs/reference/Model Providers/cloudflare.md
@@ -0,0 +1,46 @@
+# Cloudflare Workers AI
+
+Cloudflare Workers AI can be used for both chat and tab autocompletion in Continue. To setup Cloudflare Workers AI, add the following to your `config.json` file:
+
+```json title="~/.continue/config.json"
+{
+  "models": [
+    {
+      "accountId": "YOUR CLOUDFLARE ACCOUNT ID",
+      "apiKey": "YOUR CLOUDFLARE API KEY",
+      "contextLength": 2400,
+      "completionOptions": {
+        "maxTokens": 500
+      },
+      "model": "@cf/meta/llama-3-8b-instruct", // This can be the name of any model supported by Workers AI
+      "provider": "cloudflare",
+      "title": "Llama 3 8B"
+    },
+    {
+      "accountId": "YOUR CLOUDFLARE ACCOUNT ID",
+      "apiKey": "YOUR CLOUDFLARE API KEY",
+      "contextLength": 2400,
+      "completionOptions": {
+        "maxTokens": 500
+      },
+      "model": "@hf/thebloke/deepseek-coder-6.7b-instruct-awq",
+      "provider": "cloudflare",
+      "title": "DeepSeek Coder 6.7b Instruct"
+    }
+    ...
+    "tabAutocompleteModel": {
+      "accountId": "YOUR CLOUDFLARE ACCOUNT ID",
+      "apiKey": "YOUR CLOUDFLARE API KEY",
+      "model": "@hf/thebloke/deepseek-coder-6.7b-base-awq",
+      "provider": "cloudflare",
+      "title": "DeepSeek 7b"
+    },
+  ]
+}
+```
+
+Visit the [Cloudflare dashboard](https://dash.cloudflare.com/) to [create an API key](https://developers.cloudflare.com/fundamentals/api/get-started/create-token/).
+
+Review [available models](https://developers.cloudflare.com/workers-ai/models/) on Workers AI
+
+[View the source](https://github.com/continuedev/continue/blob/main/core/llm/llms/Cloudflare.ts)
diff --git a/docs/docs/walkthroughs/set-up-codestral.md b/docs/docs/walkthroughs/set-up-codestral.md
@@ -14,7 +14,7 @@ keywords: [codestral, mistral, model setup]
 
 2. Click on the gear icon in the bottom right corner of the Continue window to open `~/.continue/config.json` (MacOS) / `%userprofile%\.continue\config.json` (Windows)
 
-3. Log in and create an API key on Mistral AI's La Plateforme [here](https://console.mistral.ai/codestral)
+3. Log in and create an API key on Mistral AI's La Plateforme [here](https://console.mistral.ai/codestral). Make sure you get an API key from the "Codestral" page, as an API key for the normal "api.mistral.ai" API will not work.
 
 4. To use Codestral as your model for both `autocomplete` and `chat`, replace `[API_KEY]` with your Mistral API key below and add it to your `config.json` file:
 

diff --git a/docs/static/schemas/config.json b/docs/static/schemas/config.json
@@ -150,7 +150,8 @@
             "flowise",
             "groq",
             "fireworks",
-            "continue-proxy"
+            "continue-proxy",
+            "cloudflare"
           ],
           "markdownEnumDescriptions": [
             "### OpenAI\nUse gpt-4, gpt-3.5-turbo, or any other OpenAI model. See [here](https://openai.com/product#made-for-developers) to obtain an API key.\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/openai)",
@@ -169,7 +170,8 @@
             "### Llamafile\nTo get started with llamafiles, find and download a binary on their [GitHub repo](https://github.com/Mozilla-Ocho/llamafile#binary-instructions). Then run it with the following command:\n\n```shell\nchmod +x ./llamafile\n./llamafile\n```\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/llamafile)",
             "### Mistral API\n\nTo get access to the Mistral API, obtain your API key from the [Mistral platform](https://docs.mistral.ai/)",
             "### DeepInfra\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/deepinfra)",
-            "### Continue Proxy\n\nContinue Enterprise users can use the Continue Proxy as a single point of access to models."
+            "### Continue Proxy\n\nContinue Enterprise users can use the Continue Proxy as a single point of access to models.",
+            "### Cloudflare Workers AI\n\n[Reference](https://developers.cloudflare.com/workers-ai/)"
           ],
           "type": "string"
         },
@@ -313,7 +315,8 @@
                   "gemini",
                   "huggingface-inference-api",
                   "replicate",
-                  "together"
+                  "together",
+                  "cloudflare"
                 ]
               }
             },
@@ -359,6 +362,64 @@
             }
           }
         },
+        {
+          "if": {
+            "properties": {
+              "provider": {
+                "enum": ["cloudflare"]
+              }
+            },
+            "required": ["provider"]
+          },
+          "then": {
+            "properties": {
+              "accountId": {
+                "type": "string"
+              },
+              "model": {
+                "anyOf": [
+                  {
+                    "enum": [
+                      "@cf/meta/llama-3-8b-instruct",
+                      "@hf/thebloke/deepseek-coder-6.7b-instruct-awq",
+                      "@cf/deepseek-ai/deepseek-math-7b-instruct",
+                      "@cf/thebloke/discolm-german-7b-v1-awq",
+                      "@cf/tiiuae/falcon-7b-instruct",
+                      "@cf/google/gemma-2b-it-lora",
+                      "@hf/google/gemma-7b-it",
+                      "@cf/google/gemma-7b-it-lora",
+                      "@hf/nousresearch/hermes-2-pro-mistral-7b",
+                      "@cf/meta/llama-2-7b-chat-fp16",
+                      "@cf/meta/llama-2-7b-chat-int8",
+                      "@cf/meta-llama/llama-2-7b-chat-hf-lora",
+                      "@hf/thebloke/llama-2-13b-chat-awq",
+                      "@hf/thebloke/llamaguard-7b-awq",
+                      "@cf/mistral/mistral-7b-instruct-v0.1",
+                      "@hf/mistral/mistral-7b-instruct-v0.2",
+                      "@cf/mistral/mistral-7b-instruct-v0.2-lora",
+                      "@hf/thebloke/neural-chat-7b-v3-1-awq",
+                      "@cf/openchat/openchat-3.5-0106",
+                      "@hf/thebloke/openhermes-2.5-mistral-7b-awq",
+                      "@cf/microsoft/phi-2",
+                      "@cf/qwen/qwen1.5-0.5b-chat",
+                      "@cf/qwen/qwen1.5-1.8b-chat",
+                      "@cf/qwen/qwen1.5-7b-chat-awq",
+                      "@cf/qwen/qwen1.5-14b-chat-awq",
+                      "@cf/defog/sqlcoder-7b-2",
+                      "@hf/nexusflow/starling-lm-7b-beta",
+                      "@cf/tinyllama/tinyllama-1.1b-chat-v1.0",
+                      "@hf/thebloke/zephyr-7b-beta-awq",
+                      "@hf/thebloke/deepseek-coder-6.7b-base-awq"
+                    ]
+                  },
+                  {
+                    "type": "string"
+                  }
+                ]
+              }
+            }
+          }
+        },
         {
           "if": {
             "properties": {

diff --git a/extensions/intellij/src/main/resources/config_schema.json b/extensions/intellij/src/main/resources/config_schema.json
@@ -150,7 +150,8 @@
             "flowise",
             "groq",
             "fireworks",
-            "continue-proxy"
+            "continue-proxy",
+            "cloudflare"
           ],
           "markdownEnumDescriptions": [
             "### OpenAI\nUse gpt-4, gpt-3.5-turbo, or any other OpenAI model. See [here](https://openai.com/product#made-for-developers) to obtain an API key.\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/openai)",
@@ -169,7 +170,8 @@
             "### Llamafile\nTo get started with llamafiles, find and download a binary on their [GitHub repo](https://github.com/Mozilla-Ocho/llamafile#binary-instructions). Then run it with the following command:\n\n```shell\nchmod +x ./llamafile\n./llamafile\n```\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/llamafile)",
             "### Mistral API\n\nTo get access to the Mistral API, obtain your API key from the [Mistral platform](https://docs.mistral.ai/)",
             "### DeepInfra\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/deepinfra)",
-            "### Continue Proxy\n\nContinue Enterprise users can use the Continue Proxy as a single point of access to models."
+            "### Continue Proxy\n\nContinue Enterprise users can use the Continue Proxy as a single point of access to models.",
+            "### Cloudflare Workers AI\n\n[Reference](https://developers.cloudflare.com/workers-ai/)"
           ],
           "type": "string"
         },
@@ -313,7 +315,8 @@
                   "gemini",
                   "huggingface-inference-api",
                   "replicate",
-                  "together"
+                  "together",
+                  "cloudflare"
                 ]
               }
             },
@@ -359,6 +362,64 @@
             }
           }
         },
+        {
+          "if": {
+            "properties": {
+              "provider": {
+                "enum": ["cloudflare"]
+              }
+            },
+            "required": ["provider"]
+          },
+          "then": {
+            "properties": {
+              "accountId": {
+                "type": "string"
+              },
+              "model": {
+                "anyOf": [
+                  {
+                    "enum": [
+                      "@cf/meta/llama-3-8b-instruct",
+                      "@hf/thebloke/deepseek-coder-6.7b-instruct-awq",
+                      "@cf/deepseek-ai/deepseek-math-7b-instruct",
+                      "@cf/thebloke/discolm-german-7b-v1-awq",
+                      "@cf/tiiuae/falcon-7b-instruct",
+                      "@cf/google/gemma-2b-it-lora",
+                      "@hf/google/gemma-7b-it",
+                      "@cf/google/gemma-7b-it-lora",
+                      "@hf/nousresearch/hermes-2-pro-mistral-7b",
+                      "@cf/meta/llama-2-7b-chat-fp16",
+                      "@cf/meta/llama-2-7b-chat-int8",
+                      "@cf/meta-llama/llama-2-7b-chat-hf-lora",
+                      "@hf/thebloke/llama-2-13b-chat-awq",
+                      "@hf/thebloke/llamaguard-7b-awq",
+                      "@cf/mistral/mistral-7b-instruct-v0.1",
+                      "@hf/mistral/mistral-7b-instruct-v0.2",
+                      "@cf/mistral/mistral-7b-instruct-v0.2-lora",
+                      "@hf/thebloke/neural-chat-7b-v3-1-awq",
+                      "@cf/openchat/openchat-3.5-0106",
+                      "@hf/thebloke/openhermes-2.5-mistral-7b-awq",
+                      "@cf/microsoft/phi-2",
+                      "@cf/qwen/qwen1.5-0.5b-chat",
+                      "@cf/qwen/qwen1.5-1.8b-chat",
+                      "@cf/qwen/qwen1.5-7b-chat-awq",
+                      "@cf/qwen/qwen1.5-14b-chat-awq",
+                      "@cf/defog/sqlcoder-7b-2",
+                      "@hf/nexusflow/starling-lm-7b-beta",
+                      "@cf/tinyllama/tinyllama-1.1b-chat-v1.0",
+                      "@hf/thebloke/zephyr-7b-beta-awq",
+                      "@hf/thebloke/deepseek-coder-6.7b-base-awq"
+                    ]
+                  },
+                  {
+                    "type": "string"
+                  }
+                ]
+              }
+            }
+          }
+        },
         {
           "if": {
             "properties": {