opea-project · wanhakim · Feb 6, 2025 · Feb 5, 2025
diff --git a/sample-workflows/basic_llm_workflow.json b/sample-workflows/basic_llm_workflow.json
@@ -105,34 +105,8 @@
           {
             "label": "Model Name",
             "name": "modelName",
-            "type": "options",
+            "type": "string",
             "default": "Intel/neural-chat-7b-v3-3",
-            "options": [
-              {
-                "name": "Intel/neural-chat-7b-v3-3",
-                "label": "Intel/neural-chat-7b-v3-3"
-              },
-              {
-                "name": "Llama-2-7b-chat-hf",
-                "label": "Llama-2-7b-chat-hf"
-              },
-              {
-                "name": "Llama-2-70b-chat-hf",
-                "label": "Llama-2-70b-chat-hf"
-              },
-              {
-                "name": "Meta-Llama-3-8B-Instruct",
-                "label": "Meta-Llama-3-8B-Instruct"
-              },
-              {
-                "name": "Meta-Llama-3-70B-Instruct",
-                "label": "Meta-Llama-3-70B-Instruct"
-              },
-              {
-                "name": "Phi-3",
-                "label": "Phi-3"
-              }
-            ],
             "id": "opea_service@llm_tgi_0-input-modelName-options"
           },
           {

diff --git a/sample-workflows/sample_workflow_chatqna.json b/sample-workflows/sample_workflow_chatqna.json
@@ -361,34 +361,8 @@
           {
             "label": "Model Name",
             "name": "modelName",
-            "type": "options",
+            "type": "string",
             "default": "Intel/neural-chat-7b-v3-3",
-            "options": [
-              {
-                "name": "Intel/neural-chat-7b-v3-3",
-                "label": "Intel/neural-chat-7b-v3-3"
-              },
-              {
-                "name": "Llama-2-7b-chat-hf",
-                "label": "Llama-2-7b-chat-hf"
-              },
-              {
-                "name": "Llama-2-70b-chat-hf",
-                "label": "Llama-2-70b-chat-hf"
-              },
-              {
-                "name": "Meta-Llama-3-8B-Instruct",
-                "label": "Meta-Llama-3-8B-Instruct"
-              },
-              {
-                "name": "Meta-Llama-3-70B-Instruct",
-                "label": "Meta-Llama-3-70B-Instruct"
-              },
-              {
-                "name": "Phi-3",
-                "label": "Phi-3"
-              }
-            ],
             "id": "opea_service@llm_tgi_0-input-modelName-options"
           },
           {

diff --git a/studio-backend/app/services/exporter_service.py b/studio-backend/app/services/exporter_service.py
@@ -38,6 +38,11 @@ def convert_proj_info_to_manifest(proj_info_json, output_file=None):
                 if 'app-nginx' in metadata['name'] and output_file is None:
                     continue
                 print(f"Processing {metadata['name']} service")
+
+        # Remove HF_TOKEN if hugging_face_token is 'NA'
+        if doc.get('kind') == 'ConfigMap' and 'data' in doc:
+            if 'HF_TOKEN' in doc['data'] and doc['data']['HF_TOKEN'] == 'NA':
+                del doc['data']['HF_TOKEN']
 
         # Accumulate the YAML document in the manifest string
         manifest_string += '---\n'
@@ -81,6 +86,10 @@ def convert_proj_info_to_compose(proj_info_json, output_file=None):
 
     combined_services = {}
     for doc, service_name in (output_compose):
+        # Remove HF_TOKEN if hugging_face_token is 'NA'
+        for _, service_data in doc.items():
+            if 'environment' in service_data and 'HF_TOKEN' in service_data['environment'] and service_data['environment']['HF_TOKEN'] == 'NA':
+                del service_data['environment']['HF_TOKEN']
         combined_services.update(doc)
 
     services_data = {

diff --git a/studio-backend/app/templates/microsvc-composes/tei.yaml b/studio-backend/app/templates/microsvc-composes/tei.yaml
@@ -10,6 +10,7 @@
     no_proxy: ${no_proxy}
     http_proxy: ${http_proxy}
     https_proxy: ${https_proxy}
+    HF_TOKEN: "{{huggingFaceToken}}"
   entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id {{modelName}} --auto-truncate"
   healthcheck:
     test: ["CMD", "curl", "-f", "http://localhost:80/health"]

diff --git a/studio-backend/app/templates/microsvc-composes/tgi.yaml b/studio-backend/app/templates/microsvc-composes/tgi.yaml
@@ -1,5 +1,5 @@
 "{{endpoint}}":
-  image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+  image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
   container_name: "{{endpoint}}"
   ports:
     - "{{port}}:80"

diff --git a/studio-backend/app/templates/microsvc-manifests/tgi.yaml b/studio-backend/app/templates/microsvc-manifests/tgi.yaml
@@ -18,6 +18,8 @@ data:
   NUMBA_CACHE_DIR: "/tmp"
   HF_HOME: "/tmp/.cache/huggingface"
   CUDA_GRAPHS: "0"
+  HF_HUB_DISABLE_PROGRESS_BARS: "1"
+  HF_HUB_ENABLE_HF_TRANSFER: "0"
 ---
 # Source: tgi/templates/service.yaml
 # Copyright (C) 2024 Intel Corporation
@@ -65,7 +67,7 @@ spec:
                 name: config-{endpoint}
           securityContext:
             {}
-          image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
+          image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
           imagePullPolicy: IfNotPresent
           volumeMounts:
             - mountPath: /data

diff --git a/studio-backend/app/utils/namespace_utils.py b/studio-backend/app/utils/namespace_utils.py
@@ -1,7 +1,7 @@
 import time
 from kubernetes.client.rest import ApiException
 
-def wait_for_pod(namespace, pod_name, core_v1_api, timeout=300):
+def wait_for_pod(namespace, pod_name, core_v1_api, timeout=600):
     start_time = time.time()
     while time.time() - start_time < timeout:
         try:

diff --git a/studio-backend/tests/exporter-groundtruth/gt_app-compose.yaml b/studio-backend/tests/exporter-groundtruth/gt_app-compose.yaml
@@ -22,7 +22,7 @@ services:
       https_proxy: ${https_proxy}
     command: --model-id BAAI/bge-large-en-v1.5 --auto-truncate
   tgi-0:
-    image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     container_name: tgi-0
     ports:
     - 3081:80

diff --git a/studio-backend/tests/exporter-groundtruth/gt_app-manifest-with-nginx.yaml b/studio-backend/tests/exporter-groundtruth/gt_app-manifest-with-nginx.yaml
@@ -248,7 +248,7 @@ spec:
         - configMapRef:
             name: config-tgi-0
         securityContext: {}
-        image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+        image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
         imagePullPolicy: IfNotPresent
         volumeMounts:
         - mountPath: /data

diff --git a/studio-backend/tests/exporter-groundtruth/gt_app-manifest.yaml b/studio-backend/tests/exporter-groundtruth/gt_app-manifest.yaml
@@ -249,7 +249,7 @@ spec:
         - configMapRef:
             name: config-tgi-0
         securityContext: {}
-        image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
+        image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
         imagePullPolicy: IfNotPresent
         volumeMounts:
         - mountPath: /data

diff --git a/studio-backend/tests/flowise-pipeline-translator/flowise_pipeline.json b/studio-backend/tests/flowise-pipeline-translator/flowise_pipeline.json
diff --git a/studio-frontend/packages/server/src/nodes/llm.js b/studio-frontend/packages/server/src/nodes/llm.js
diff --git a/tests/playwright/studio-e2e/001_test_sandbox_deployment.spec.ts b/tests/playwright/studio-e2e/001_test_sandbox_deployment.spec.ts
@@ -5,7 +5,7 @@ import path from 'path';
 import os from 'os';
 
 test('001_test_sandbox_deployment', async ({ browser, baseURL }) => {
-    test.setTimeout(600000);
+    test.setTimeout(1200000);
     const context = await browser.newContext({
         ignoreHTTPSErrors: true
     });
@@ -38,7 +38,7 @@ test('001_test_sandbox_deployment', async ({ browser, baseURL }) => {
     //         console.log(`Attempt ${i + 1} failed: ${error}`);
     //     }
     // }
-    await waitForStatusText(page, 'td.MuiTableCell-root div.MuiStack-root p.MuiTypography-root', 'Ready', 5, 60000);
+    await waitForStatusText(page, 'td.MuiTableCell-root div.MuiStack-root p.MuiTypography-root', 'Ready', 10, 60000);
     await page.waitForTimeout(8000);
 
     // Open APP-UI

diff --git a/tests/playwright/studio-e2e/002_test_sandbox_chatqna.spec.ts b/tests/playwright/studio-e2e/002_test_sandbox_chatqna.spec.ts
@@ -38,7 +38,7 @@ async function setupResponseListener(page, apiResponse) {
 }
 
 test('002_test_sandbox_chatqna', async ({ browser, baseURL }) => {
-    test.setTimeout(600000);
+    test.setTimeout(1200000);
     let apiResponse = { value: '' };
     const context = await browser.newContext({
         ignoreHTTPSErrors: true
@@ -63,7 +63,7 @@ test('002_test_sandbox_chatqna', async ({ browser, baseURL }) => {
     await page.goto(IDC_URL);
     await expect(page.locator('td.MuiTableCell-root div.MuiStack-root p.MuiTypography-root').first()).toHaveText('Not Running', { timeout: 60000 });
     await page.getByLabel('a dense table').locator('button').first().click();
-    await waitForStatusText(page, 'td.MuiTableCell-root div.MuiStack-root p.MuiTypography-root', 'Ready', 5, 60000);
+    await waitForStatusText(page, 'td.MuiTableCell-root div.MuiStack-root p.MuiTypography-root', 'Ready', 10, 60000);
     await page.waitForTimeout(10000);
 
     // Open APP-UI

diff --git a/tests/playwright/utils.ts b/tests/playwright/utils.ts
@@ -1,6 +1,6 @@
 import { expect } from '@playwright/test';
 
-export async function waitForStatusText(page: any, selector: string, statusText: string, maxAttempts: number = 5, intervalTimeout: number = 60000) {
+export async function waitForStatusText(page: any, selector: string, statusText: string, maxAttempts: number = 10, intervalTimeout: number = 60000) {
     for (let i = 0; i < maxAttempts; i++) {
         try {
             const text = await page.locator(selector).first().innerText();