Merge branch 'concedo_experimental' into croco_nex_0

Author: Nexesenex

Diff for: examples/server/public/index.html.gz

@@ -334,24 +334,24 @@ struct server_task {
         if (data.contains("json_schema") && !data.contains("grammar")) {
             try {
                 auto schema                  = json_value(data, "json_schema", json::object());
-                LOG_DBG("JSON schema: %s\n", schema.dump(2).c_str());
+                SRV_DBG("JSON schema: %s\n", schema.dump(2).c_str());
                 params.sampling.grammar      = json_schema_to_grammar(schema);
-                LOG_DBG("Converted grammar: %s\n", params.sampling.grammar.c_str());
+                SRV_DBG("Converted grammar: %s\n", params.sampling.grammar.c_str());
             } catch (const std::exception & e) {
                 throw std::runtime_error(std::string("\"json_schema\": ") + e.what());
             }
         } else {
             params.sampling.grammar      = json_value(data, "grammar", defaults.sampling.grammar);
-            LOG_DBG("Grammar: %s\n", params.sampling.grammar.c_str());
+            SRV_DBG("Grammar: %s\n", params.sampling.grammar.c_str());
             params.sampling.grammar_lazy = json_value(data, "grammar_lazy", defaults.sampling.grammar_lazy);
-            LOG_DBG("Grammar lazy: %s\n", params.sampling.grammar_lazy ? "true" : "false");
+            SRV_DBG("Grammar lazy: %s\n", params.sampling.grammar_lazy ? "true" : "false");
         }
 
         {
             auto it = data.find("chat_format");
             if (it != data.end()) {
                 params.oaicompat_chat_format = static_cast<common_chat_format>(it->get<int>());
-                LOG_INF("Chat format: %s\n", common_chat_format_name(params.oaicompat_chat_format).c_str());
+                SRV_INF("Chat format: %s\n", common_chat_format_name(params.oaicompat_chat_format).c_str());
             } else {
                 params.oaicompat_chat_format = defaults.oaicompat_chat_format;
             }
@@ -367,12 +367,12 @@ struct server_task {
 
                     auto ids = common_tokenize(vocab, trigger.word, /* add_special= */ false, /* parse_special= */ true);
                     if (ids.size() == 1) {
-                        LOG_DBG("Grammar trigger token: %d (`%s`)\n", ids[0], trigger.word.c_str());
+                        SRV_DBG("Grammar trigger token: %d (`%s`)\n", ids[0], trigger.word.c_str());
                         params.sampling.grammar_trigger_tokens.push_back(ids[0]);
                         params.sampling.preserved_tokens.insert(ids[0]);
                         continue;
                     }
-                    LOG_DBG("Grammar trigger word: `%s`\n", trigger.word.c_str());
+                    SRV_DBG("Grammar trigger word: `%s`\n", trigger.word.c_str());
                     params.sampling.grammar_trigger_words.push_back(trigger);
                 }
             }
@@ -381,11 +381,11 @@ struct server_task {
                 for (const auto & t : *preserved_tokens) {
                     auto ids = common_tokenize(vocab, t.get<std::string>(), /* add_special= */ false, /* parse_special= */ true);
                     if (ids.size() == 1) {
-                        LOG_DBG("Preserved token: %d\n", ids[0]);
+                        SRV_DBG("Preserved token: %d\n", ids[0]);
                         params.sampling.preserved_tokens.insert(ids[0]);
                     } else {
                         // This may happen when using a tool call style meant for a model with special tokens to preserve on a model without said tokens.
-                        LOG_WRN("Not preserved because more than 1 token (wrong chat template override?): %s\n", t.get<std::string>().c_str());
+                        SRV_WRN("Not preserved because more than 1 token (wrong chat template override?): %s\n", t.get<std::string>().c_str());
                     }
                 }
             }
@@ -717,7 +717,7 @@ struct server_task_result_cmpl_final : server_task_result {
         std::string finish_reason = "length";
         common_chat_msg msg;
         if (stop == STOP_TYPE_WORD || stop == STOP_TYPE_EOS) {
-            LOG_DBG("Parsing chat message: %s\n", content.c_str());
+            SRV_DBG("Parsing chat message: %s\n", content.c_str());
             msg = common_chat_parse(content, oaicompat_chat_format);
             finish_reason = msg.tool_calls.empty() ? "stop" : "tool_calls";
         } else {
@@ -1885,7 +1885,7 @@ struct server_context {
         }
 
         if (params_base.chat_template.empty() && !validate_builtin_chat_template(params.use_jinja)) {
-            LOG_WRN("%s: The chat template that comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses\n", __func__);
+            SRV_WRN("%s: The chat template that comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses\n", __func__);
             chat_templates = common_chat_templates_from_model(model, "chatml");
         } else {
             chat_templates = common_chat_templates_from_model(model, params_base.chat_template);
@@ -3355,10 +3355,10 @@ static void log_server_request(const httplib::Request & req, const httplib::Resp
 
     // reminder: this function is not covered by httplib's exception handler; if someone does more complicated stuff, think about wrapping it in try-catch
 
-    LOG_INF("request: %s %s %s %d\n", req.method.c_str(), req.path.c_str(), req.remote_addr.c_str(), res.status);
+    SRV_INF("request: %s %s %s %d\n", req.method.c_str(), req.path.c_str(), req.remote_addr.c_str(), res.status);
 
-    LOG_DBG("request:  %s\n", req.body.c_str());
-    LOG_DBG("response: %s\n", res.body.c_str());
+    SRV_DBG("request:  %s\n", req.body.c_str());
+    SRV_DBG("response: %s\n", res.body.c_str());
 }
 
 std::function<void(int)> shutdown_handler;
@@ -3860,7 +3860,9 @@ int main(int argc, char ** argv) {
 
         try {
             const auto & prompt = data.at("prompt");
-            LOG_DBG("Prompt: %s\n", prompt.is_string() ? prompt.get<std::string>().c_str() : prompt.dump(2).c_str());
+            // TODO: this log can become very long, put it behind a flag or think about a more compact format
+            //SRV_DBG("Prompt: %s\n", prompt.is_string() ? prompt.get<std::string>().c_str() : prompt.dump(2).c_str());
+
             std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.vocab, prompt, true, true);
             tasks.reserve(tokenized_prompts.size());
             for (size_t i = 0; i < tokenized_prompts.size(); i++) {
@@ -4376,6 +4378,9 @@ int main(int argc, char ** argv) {
                     res.set_content("Error: gzip is not supported by this browser", "text/plain");
                 } else {
                     res.set_header("Content-Encoding", "gzip");
+                    // COEP and COOP headers, required by pyodide (python interpreter)
+                    res.set_header("Cross-Origin-Embedder-Policy", "require-corp");
+                    res.set_header("Cross-Origin-Opener-Policy", "same-origin");
                     res.set_content(reinterpret_cast<const char*>(index_html_gz), index_html_gz_len, "text/html; charset=utf-8");
                 }
                 return false;

Diff for: examples/server/server.cpp

@@ -11,6 +11,7 @@
     "preview": "vite preview"
   },
   "dependencies": {
+    "@heroicons/react": "^2.2.0",
     "@sec-ant/readable-stream": "^0.6.0",
     "@vscode/markdown-it-katex": "^1.1.1",
     "autoprefixer": "^10.4.20",

Diff for: examples/server/webui/package-lock.json

@@ -1,8 +1,9 @@
 import { HashRouter, Outlet, Route, Routes } from 'react-router';
 import Header from './components/Header';
 import Sidebar from './components/Sidebar';
-import { AppContextProvider } from './utils/app.context';
+import { AppContextProvider, useAppContext } from './utils/app.context';
 import ChatScreen from './components/ChatScreen';
+import SettingDialog from './components/SettingDialog';
 
 function App() {
   return (
@@ -22,13 +23,23 @@ function App() {
 }
 
 function AppLayout() {
+  const { showSettings, setShowSettings } = useAppContext();
   return (
     <>
       <Sidebar />
-      <div className="chat-screen drawer-content grow flex flex-col h-screen w-screen mx-auto px-4">
+      <div
+        className="drawer-content grow flex flex-col h-screen w-screen mx-auto px-4 overflow-auto"
+        id="main-scroll"
+      >
         <Header />
         <Outlet />
       </div>
+      {
+        <SettingDialog
+          show={showSettings}
+          onClose={() => setShowSettings(false)}
+        />
+      }
     </>
   );
 }

Diff for: examples/server/webui/package.json

@@ -10,6 +10,7 @@ export const BASE_URL = new URL('.', document.baseURI).href
 
 export const CONFIG_DEFAULT = {
   // Note: in order not to introduce breaking changes, please keep the same data type (number, string, etc) if you want to change the default value. Do not use null or undefined for default value.
+  // Do not use nested objects, keep it single level. Prefix the key if you need to group them.
   apiKey: '',
   systemMessage: 'You are a helpful assistant.',
   showTokensPerSecond: false,
@@ -36,6 +37,8 @@ export const CONFIG_DEFAULT = {
   dry_penalty_last_n: -1,
   max_tokens: -1,
   custom: '', // custom json-stringified object
+  // experimental features
+  pyIntepreterEnabled: false,
 };
 export const CONFIG_INFO: Record<string, string> = {
   apiKey: 'Set the API Key if you are using --api-key option for the server.',

Diff for: examples/server/webui/src/App.tsx

@@ -0,0 +1,195 @@
+import { useEffect, useState } from 'react';
+import { useAppContext } from '../utils/app.context';
+import { OpenInNewTab, XCloseButton } from '../utils/common';
+import { CanvasType } from '../utils/types';
+import { PlayIcon, StopIcon } from '@heroicons/react/24/outline';
+import StorageUtils from '../utils/storage';
+
+const canInterrupt = typeof SharedArrayBuffer === 'function';
+
+// adapted from https://pyodide.org/en/stable/usage/webworker.html
+const WORKER_CODE = `
+importScripts("https://cdn.jsdelivr.net/pyodide/v0.27.2/full/pyodide.js");
+
+let stdOutAndErr = [];
+
+let pyodideReadyPromise = loadPyodide({
+  stdout: (data) => stdOutAndErr.push(data),
+  stderr: (data) => stdOutAndErr.push(data),
+});
+
+let alreadySetBuff = false;
+
+self.onmessage = async (event) => {
+  stdOutAndErr = [];
+
+  // make sure loading is done
+  const pyodide = await pyodideReadyPromise;
+  const { id, python, context, interruptBuffer } = event.data;
+
+  if (interruptBuffer && !alreadySetBuff) {
+    pyodide.setInterruptBuffer(interruptBuffer);
+    alreadySetBuff = true;
+  }
+
+  // Now load any packages we need, run the code, and send the result back.
+  await pyodide.loadPackagesFromImports(python);
+
+  // make a Python dictionary with the data from content
+  const dict = pyodide.globals.get("dict");
+  const globals = dict(Object.entries(context));
+  try {
+    self.postMessage({ id, running: true });
+    // Execute the python code in this context
+    const result = pyodide.runPython(python, { globals });
+    self.postMessage({ result, id, stdOutAndErr });
+  } catch (error) {
+    self.postMessage({ error: error.message, id });
+  }
+  interruptBuffer[0] = 0;
+};
+`;
+
+let worker: Worker;
+const interruptBuffer = canInterrupt
+  ? new Uint8Array(new SharedArrayBuffer(1))
+  : null;
+
+const startWorker = () => {
+  if (!worker) {
+    worker = new Worker(
+      URL.createObjectURL(new Blob([WORKER_CODE], { type: 'text/javascript' }))
+    );
+  }
+};
+
+if (StorageUtils.getConfig().pyIntepreterEnabled) {
+  startWorker();
+}
+
+const runCodeInWorker = (
+  pyCode: string,
+  callbackRunning: () => void
+): {
+  donePromise: Promise<string>;
+  interrupt: () => void;
+} => {
+  startWorker();
+  const id = Math.random() * 1e8;
+  const context = {};
+  if (interruptBuffer) {
+    interruptBuffer[0] = 0;
+  }
+
+  const donePromise = new Promise<string>((resolve) => {
+    worker.onmessage = (event) => {
+      const { error, stdOutAndErr, running } = event.data;
+      if (id !== event.data.id) return;
+      if (running) {
+        callbackRunning();
+        return;
+      } else if (error) {
+        resolve(error.toString());
+      } else {
+        resolve(stdOutAndErr.join('\n'));
+      }
+    };
+    worker.postMessage({ id, python: pyCode, context, interruptBuffer });
+  });
+
+  const interrupt = () => {
+    console.log('Interrupting...');
+    console.trace();
+    if (interruptBuffer) {
+      interruptBuffer[0] = 2;
+    }
+  };
+
+  return { donePromise, interrupt };
+};
+
+export default function CanvasPyInterpreter() {
+  const { canvasData, setCanvasData } = useAppContext();
+
+  const [code, setCode] = useState(canvasData?.content ?? ''); // copy to avoid direct mutation
+  const [running, setRunning] = useState(false);
+  const [output, setOutput] = useState('');
+  const [interruptFn, setInterruptFn] = useState<() => void>();
+  const [showStopBtn, setShowStopBtn] = useState(false);
+
+  const runCode = async (pycode: string) => {
+    interruptFn?.();
+    setRunning(true);
+    setOutput('Loading Pyodide...');
+    const { donePromise, interrupt } = runCodeInWorker(pycode, () => {
+      setOutput('Running...');
+      setShowStopBtn(canInterrupt);
+    });
+    setInterruptFn(() => interrupt);
+    const out = await donePromise;
+    setOutput(out);
+    setRunning(false);
+    setShowStopBtn(false);
+  };
+
+  // run code on mount
+  useEffect(() => {
+    setCode(canvasData?.content ?? '');
+    runCode(canvasData?.content ?? '');
+    // eslint-disable-next-line react-hooks/exhaustive-deps
+  }, [canvasData?.content]);
+
+  if (canvasData?.type !== CanvasType.PY_INTERPRETER) {
+    return null;
+  }
+
+  return (
+    <div className="card bg-base-200 w-full h-full shadow-xl">
+      <div className="card-body">
+        <div className="flex justify-between items-center mb-4">
+          <span className="text-lg font-bold">Python Interpreter</span>
+          <XCloseButton
+            className="bg-base-100"
+            onClick={() => setCanvasData(null)}
+          />
+        </div>
+        <div className="grid grid-rows-3 gap-4 h-full">
+          <textarea
+            className="textarea textarea-bordered w-full h-full font-mono"
+            value={code}
+            onChange={(e) => setCode(e.target.value)}
+          ></textarea>
+          <div className="font-mono flex flex-col row-span-2">
+            <div className="flex items-center mb-2">
+              <button
+                className="btn btn-sm bg-base-100"
+                onClick={() => runCode(code)}
+                disabled={running}
+              >
+                <PlayIcon className="h-6 w-6" /> Run
+              </button>
+              {showStopBtn && (
+                <button
+                  className="btn btn-sm bg-base-100 ml-2"
+                  onClick={() => interruptFn?.()}
+                >
+                  <StopIcon className="h-6 w-6" /> Stop
+                </button>
+              )}
+              <span className="grow text-right text-xs">
+                <OpenInNewTab href="https://github.com/ggerganov/llama.cpp/issues/11762">
+                  Report a bug
+                </OpenInNewTab>
+              </span>
+            </div>
+            <textarea
+              className="textarea textarea-bordered h-full dark-color"
+              value={output}
+              readOnly
+            ></textarea>
+          </div>
+        </div>
+      </div>
+    </div>
+  );
+}