Merge pull request #32 from mlrun/main

merge main

Author: daniels290813

env.template

@@ -1,3 +1,6 @@
-S3_BUCKET_NAME=
 OPENAI_API_BASE=
-OPENAI_API_KEY=
+OPENAI_API_KEY=
+#for platform Iguazio, you need to set the MYSQL_URL and remove S3_BUCKET_NAME
+MYSQL_URL=
+#for platform Mck, you need to set the S3_BUCKET_NAME and remove MYSQL_URL
+S3_BUCKET_NAME=

mlrun.env

@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "aed64e7c-1706-4a78-89ff-75b8a382472a",
    "metadata": {
     "jupyter": {
@@ -62,7 +62,7 @@
    },
    "outputs": [],
    "source": [
-    "# !pip install SQLAlchemy==2.0.31 pymysql"
+    "!pip install SQLAlchemy==2.0.31 pymysql dotenv"
    ]
   },
   {
@@ -90,7 +90,8 @@
     "- This demo is limited to run with MLRun 1.9.x Python 3.11, with CPU, a mysql database and run the pipeline with `engine = \"remote\"`.\n",
     "- GPU is not supported at the moment.\n",
     "- Need to setup a mysql database for the demo. sqlite is not supported now.\n",
-    "- Please set `run_with_gpu = False`, `use_sqlite = False`, `engine = \"remote\"`"
+    "- Please set `run_with_gpu = False`, `use_sqlite = False`, `engine = \"remote\"`\n",
+    "- .env include OPENAI_API_KEY, OPENAI_API_BASE, and MYSQL_URL"
    ]
   },
   {
@@ -108,7 +109,8 @@
    "source": [
     "- GPU is not supported at the moment.\n",
     "- sqlite is supported.\n",
-    "- Please set `run_with_gpu = False`, `use_sqlite = True`, `engine = \"remote\"`"
+    "- Please set `run_with_gpu = False`, `use_sqlite = True`, `engine = \"remote\"`\n",
+    "- .env include OPENAI_API_KEY, OPENAI_API_BASE, and S3_BUCKET_NAME"
    ]
   },
   {
@@ -140,21 +142,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "76f05c23312057a3",
    "metadata": {},
    "outputs": [],
    "source": [
     "# True = run with GPU, False = run with CPU\n",
     "run_with_gpu = False\n",
     "language = \"en\" # The languages of the calls, es - Spanish, en - English\n",
-    "skip_calls_generation = False\n",
-    "use_sqlite = False"
+    "skip_calls_generation = False"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "7e7503f4-8830-4972-a986-10f4c29624b9",
    "metadata": {
     "tags": []
@@ -166,7 +167,7 @@
        "True"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -176,7 +177,6 @@
     "import os\n",
     "import sys\n",
     "import mlrun\n",
-    "\n",
     "dotenv_file = \".env\"\n",
     "sys.path.insert(0, os.path.abspath(\"./\"))\n",
     "\n",
@@ -185,7 +185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "d33fc614-2898-4b12-b34f-62181651a9b5",
    "metadata": {},
    "outputs": [],
@@ -195,6 +195,20 @@
     "assert os.environ[\"OPENAI_API_KEY\"]"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9e2a5fd0-f4ff-486a-9d22-e5b80b7eb2a4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not mlrun.mlconf.is_ce_mode():\n",
+    "    assert os.environ[\"MYSQL_URL\"]\n",
+    "    use_sqlite = False\n",
+    "else:\n",
+    "    use_sqlite = True"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1ea33fee-ec95-48e3-aae8-9247ae182481",
@@ -230,7 +244,6 @@
    "execution_count": null,
    "id": "80b388f8-5aa3-4b6a-9b6d-b6dca242165e",
    "metadata": {
-    "scrolled": true,
     "tags": []
    },
    "outputs": [],
@@ -239,6 +252,7 @@
     "project = mlrun.get_or_create_project(\n",
     "    name=project_name,\n",
     "    user_project=False,\n",
+    "    allow_cross_project=True,\n",
     "    parameters={\n",
     "        \"build_image\": True,\n",
     "        \"source\": \"git://github.com/mlrun/demo-call-center.git#main\",\n",
@@ -296,7 +310,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 14,
    "id": "adc25213-d4d6-411d-a9b0-edf91007ba33",
    "metadata": {},
    "outputs": [],
@@ -343,21 +357,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "8d3d7cca-ff52-4ffd-98df-7d70e8b083cf",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<mlrun.projects.project.MlrunProject at 0x7fa2d60f05d0>"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "project.spec.params['build_image']=False\n",
     "project.save()"
@@ -555,21 +558,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "id": "399ed9c3-2765-4f03-a812-79428e51149e",
    "metadata": {
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "> 2025-08-18 03:40:34,753 [info] downloading s3://igz1-xingsheng-medium-r/projects/call-center-demo/artifacts/582022de-ef13-47b9-8b63-dbcf8680135e/text-to-audio/0/audio_files.zip to local temp file\n",
-      "> 2025-08-18 03:40:37,898 [info] downloading s3://igz1-xingsheng-medium-r/projects/call-center-demo/artifacts/582022de-ef13-47b9-8b63-dbcf8680135e/conversation-generation/0/conversations.zip to local temp file\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import zipfile\n",
     "\n",
@@ -669,9 +663,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "mlrun",
+   "display_name": "py311",
    "language": "python",
-   "name": "mlrun"
+   "name": "conda-env-.conda-py311-py"
   },
   "language_info": {
    "codemirror_mode": {

notebook.ipynb

@@ -50,7 +50,7 @@ def setup(
     if use_sqlite:
         # uploading db file to s3:
         if CE_MODE:
-            s3 = boto3.client("s3") if not os.getenv("S3_ENDPOINT_URL") else boto3.client('s3', endpoint_url=os.getenv("S3_ENDPOINT_URL"))
+            s3 = boto3.client("s3") if not os.getenv("AWS_ENDPOINT_URL_S3") else boto3.client('s3', endpoint_url=os.getenv("AWS_ENDPOINT_URL_S3"))
             bucket_name = Path(mlrun.mlconf.artifact_path).parts[1]
             # Upload the file
             s3.upload_file(
@@ -150,11 +150,15 @@ def _build_image(project: mlrun.projects.MlrunProject, with_gpu: bool, default_i
     ] if with_gpu else []
 
     other_requirements = [
-        "pip install mlrun langchain==0.2.17 openai==1.58.1 langchain_community==0.2.19 pydub==0.25.1 streamlit==1.28.0 st-annotated-text==4.0.1 spacy==3.7.2 librosa==0.10.1 presidio-anonymizer==2.2.34 presidio-analyzer==2.2.34 nltk==3.8.1 flair==0.13.0 htbuilder==0.6.2",
-        "python -m spacy download en_core_web_lg",
+        "pip install mlrun langchain==0.2.17 openai==1.58.1 langchain_community==0.2.19 pydub==0.25.1 streamlit==1.28.0 st-annotated-text==4.0.1 spacy==3.7.1 librosa==0.10.1 presidio-anonymizer==2.2.34 presidio-analyzer==2.2.34 nltk==3.8.1 flair==0.13.0 htbuilder==0.6.2",
+        "pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.7.1/en_core_web_lg-3.7.1.tar.gz",
+        # "python -m spacy download en_core_web_lg",
+
         "pip install SQLAlchemy==2.0.31 pymysql requests_toolbelt==0.10.1",
         "pip uninstall -y onnxruntime-gpu onnxruntime",
         f"pip install {config['onnx_package']}",
+        "pip uninstall -y protobuf",
+        "pip install protobuf"
     ]    
 
     # Combine commands in the required order
@@ -357,4 +361,4 @@ def _set_workflows(project: mlrun.projects.MlrunProject, image):
     )
     project.set_workflow(
         name="calls-analysis", workflow_path="./src/workflows/calls_analysis.py", image=image
-    )
+    )