Skip to content

Harden TechJournalist media bootstrap per PR #537 review feedback #540

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
leestott merged 2 commits into from
May 13, 2026
+33 −2
Merged

Harden TechJournalist media bootstrap per PR #537 review feedback #540

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ef0b3da
Initial plan
Copilot May 13, 2026
c89036e
fix: address PR 537 review comments in Phi-4 journalist notebook
Copilot May 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 33 additions & 2 deletions md/02.Application/08.Multimodel/Phi4/TechJournalist/phi_4_mm_audio_text_publish_news.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,7 +224,9 @@
"outputs": [],
"source": [
"import requests\n",
"import urllib.request\n",
"import torch\n",
"from pathlib import Path\n",
"from PIL import Image\n",
"import soundfile\n",
"from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig,pipeline,AutoTokenizer"
Expand Down Expand Up @@ -360,6 +362,34 @@
"prompt = f'{system_prompt}You are a technology journalist who writes professional content based on audio and picture content{prompt_suffix}{user_prompt}Reorganize the content provided by audio <|audio_1|> and image <|image_1|> from a professional perspective and write a press release based on the current development of AI ,output is markdown format and including title and content {prompt_suffix}{assistant_prompt}'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"media_dir = Path(\"media\")\n",
"media_dir.mkdir(exist_ok=True)\n",
"\n",
"image_path = media_dir / \"copilot.png\"\n",
"audio_path = media_dir / \"sample_audio.mp3\"\n",
"\n",
"sample_media = {\n",
" image_path: \"https://raw.githubusercontent.com/microsoft/PhiCookBook/main/imgs/02/pfonnx/pfv.png\",\n",
" audio_path: \"https://raw.githubusercontent.com/Azure-Samples/cognitive-services-speech-sdk/master/samples/csharp/sharedcontent/console/whatstheweatherlike.mp3\",\n",
"}\n",
"\n",
"for path, url in sample_media.items():\n",
" if not path.exists():\n",
" try:\n",
" with urllib.request.urlopen(url, timeout=30) as response, open(path, \"wb\") as out_file:\n",
" out_file.write(response.read())\n",
" except Exception as exc:\n",
" raise RuntimeError(\n",
" f\"Failed to download {path.name} from {url}. Download it manually and place it under {media_dir}/\"\n",
" ) from exc"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand All @@ -368,7 +398,8 @@
},
"outputs": [],
"source": [
"image = Image.open(\"./copilot.png\")"
"with Image.open(image_path) as img:\n",
" image = img.copy()"
]
},
{
Expand All @@ -379,7 +410,7 @@
},
"outputs": [],
"source": [
"audio = soundfile.read('./satya1.mp3')"
"audio = soundfile.read(audio_path)"
]
},
{
Expand Down