Simplified based on latest Gradio, and added PC fix for audio playback
This commit is contained in:
Edward Donner
158
week2/day5.ipynb
158
week2/day5.ipynb
@@ -60,16 +60,14 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This function looks rather simpler than the one from my video, because we're taking advantage of the latest Gradio updates\n",
|
||||
"\n",
|
||||
"def chat(message, history):\n",
|
||||
" messages = [{\"role\": \"system\", \"content\": system_message}]\n",
|
||||
" for human, assistant in history:\n",
|
||||
" messages.append({\"role\": \"user\", \"content\": human})\n",
|
||||
" messages.append({\"role\": \"assistant\", \"content\": assistant})\n",
|
||||
" messages.append({\"role\": \"user\", \"content\": message})\n",
|
||||
" messages = [{\"role\": \"system\", \"content\": system_message}] + history + [{\"role\": \"user\", \"content\": message}]\n",
|
||||
" response = openai.chat.completions.create(model=MODEL, messages=messages)\n",
|
||||
" return response.choices[0].message.content\n",
|
||||
"\n",
|
||||
"gr.ChatInterface(fn=chat).launch()"
|
||||
"gr.ChatInterface(fn=chat, type=\"messages\").launch()"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -175,11 +173,7 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def chat(message, history):\n",
|
||||
" messages = [{\"role\": \"system\", \"content\": system_message}]\n",
|
||||
" for human, assistant in history:\n",
|
||||
" messages.append({\"role\": \"user\", \"content\": human})\n",
|
||||
" messages.append({\"role\": \"assistant\", \"content\": assistant})\n",
|
||||
" messages.append({\"role\": \"user\", \"content\": message})\n",
|
||||
" messages = [{\"role\": \"system\", \"content\": system_message}] + history + [{\"role\": \"user\", \"content\": message}]\n",
|
||||
" response = openai.chat.completions.create(model=MODEL, messages=messages, tools=tools)\n",
|
||||
"\n",
|
||||
" if response.choices[0].finish_reason==\"tool_calls\":\n",
|
||||
@@ -221,7 +215,7 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"gr.ChatInterface(fn=chat).launch()"
|
||||
"gr.ChatInterface(fn=chat, type=\"messages\").launch()"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -333,6 +327,18 @@
|
||||
"Message me or email me at ed@edwarddonner.com with any problems!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d91d3f8f-e505-4e3c-a87c-9e42ed823db6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# For Mac users\n",
|
||||
"\n",
|
||||
"This version should work fine for you. It might work for Windows users too, but you might get a Permissions error writing to a temp file. If so, see the next section!\n",
|
||||
"\n",
|
||||
"As always, if you have problems, please contact me! (You could also comment out the audio talker() in the later code if you're less interested in audio generation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@@ -365,6 +371,67 @@
|
||||
"talker(\"Well, hi there\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ad89a9bd-bb1e-4bbb-a49a-83af5f500c24",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# For Windows users\n",
|
||||
"\n",
|
||||
"## if you get a permissions error writing to a temp file, then this code should work instead.\n",
|
||||
"\n",
|
||||
"A collaboration between student Mark M. and Claude got this resolved!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d59c8ebd-79c5-498a-bdf2-3a1c50d91aa0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import tempfile\n",
|
||||
"import subprocess\n",
|
||||
"\n",
|
||||
"def play_audio(audio_segment):\n",
|
||||
" temp_dir = tempfile.gettempdir()\n",
|
||||
" temp_path = os.path.join(temp_dir, \"temp_audio.wav\")\n",
|
||||
" try:\n",
|
||||
" audio_segment.export(temp_path, format=\"wav\")\n",
|
||||
" subprocess.call([\n",
|
||||
" \"ffplay\",\n",
|
||||
" \"-nodisp\",\n",
|
||||
" \"-autoexit\",\n",
|
||||
" \"-hide_banner\",\n",
|
||||
" temp_path\n",
|
||||
" ], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)\n",
|
||||
" finally:\n",
|
||||
" try:\n",
|
||||
" os.remove(temp_path)\n",
|
||||
" except Exception:\n",
|
||||
" pass\n",
|
||||
" \n",
|
||||
"def talker(message):\n",
|
||||
" response = openai.audio.speech.create(\n",
|
||||
" model=\"tts-1\",\n",
|
||||
" voice=\"onyx\", # Also, try replacing onyx with alloy\n",
|
||||
" input=message\n",
|
||||
" )\n",
|
||||
" audio_stream = BytesIO(response.content)\n",
|
||||
" audio = AudioSegment.from_file(audio_stream, format=\"mp3\")\n",
|
||||
" play_audio(audio)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0dfb8ee9-e7dd-4615-8d69-2deb3fd44473",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"talker(\"Well hi there\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1d48876d-c4fa-46a8-a04f-f9fadf61fb0d",
|
||||
@@ -390,26 +457,23 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def chat(message, history):\n",
|
||||
"def chat(history):\n",
|
||||
" messages = [{\"role\": \"system\", \"content\": system_message}] + history\n",
|
||||
" response = openai.chat.completions.create(model=MODEL, messages=messages, tools=tools)\n",
|
||||
" image = None\n",
|
||||
" conversation = [{\"role\": \"system\", \"content\": system_message}]\n",
|
||||
" for human, assistant in history:\n",
|
||||
" conversation.append({\"role\": \"user\", \"content\": human})\n",
|
||||
" conversation.append({\"role\": \"assistant\", \"content\": assistant})\n",
|
||||
" conversation.append({\"role\": \"user\", \"content\": message})\n",
|
||||
" response = openai.chat.completions.create(model=MODEL, messages=conversation, tools=tools)\n",
|
||||
"\n",
|
||||
" \n",
|
||||
" if response.choices[0].finish_reason==\"tool_calls\":\n",
|
||||
" message = tool_call = response.choices[0].message\n",
|
||||
" message = response.choices[0].message\n",
|
||||
" response, city = handle_tool_call(message)\n",
|
||||
" conversation.append(message)\n",
|
||||
" conversation.append(response)\n",
|
||||
" messages.append(message)\n",
|
||||
" messages.append(response)\n",
|
||||
" image = artist(city)\n",
|
||||
" response = openai.chat.completions.create(model=MODEL, messages=conversation)\n",
|
||||
"\n",
|
||||
" response = openai.chat.completions.create(model=MODEL, messages=messages)\n",
|
||||
" \n",
|
||||
" reply = response.choices[0].message.content\n",
|
||||
" history += [{\"role\":\"assistant\", \"content\":reply}]\n",
|
||||
" talker(reply)\n",
|
||||
" return reply, image"
|
||||
" return history, image"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -419,41 +483,43 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# More involved Gradio code as we're not using the preset Chat interface\n",
|
||||
"# More involved Gradio code as we're not using the preset Chat interface!\n",
|
||||
"# Passing in inbrowser=True in the last line will cause a Gradio window to pop up immediately.\n",
|
||||
"\n",
|
||||
"with gr.Blocks() as ui:\n",
|
||||
" with gr.Row():\n",
|
||||
" chatbot = gr.Chatbot(height=500)\n",
|
||||
" chatbot = gr.Chatbot(height=500, type=\"messages\")\n",
|
||||
" image_output = gr.Image(height=500)\n",
|
||||
" with gr.Row():\n",
|
||||
" msg = gr.Textbox(label=\"Chat with our AI Assistant:\")\n",
|
||||
" entry = gr.Textbox(label=\"Chat with our AI Assistant:\")\n",
|
||||
" with gr.Row():\n",
|
||||
" clear = gr.Button(\"Clear\")\n",
|
||||
"\n",
|
||||
" def user(user_message, history):\n",
|
||||
" return \"\", history + [[user_message, None]]\n",
|
||||
" def do_entry(message, history):\n",
|
||||
" history += [{\"role\":\"user\", \"content\":message}]\n",
|
||||
" return \"\", history\n",
|
||||
"\n",
|
||||
" def bot(history):\n",
|
||||
" user_message = history[-1][0]\n",
|
||||
" bot_message, image = chat(user_message, history[:-1])\n",
|
||||
" history[-1][1] = bot_message\n",
|
||||
" return history, image\n",
|
||||
"\n",
|
||||
" msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(\n",
|
||||
" bot, chatbot, [chatbot, image_output]\n",
|
||||
" entry.submit(do_entry, inputs=[entry, chatbot], outputs=[entry, chatbot]).then(\n",
|
||||
" chat, inputs=chatbot, outputs=[chatbot, image_output]\n",
|
||||
" )\n",
|
||||
" clear.click(lambda: None, None, chatbot, queue=False)\n",
|
||||
" clear.click(lambda: None, inputs=None, outputs=chatbot, queue=False)\n",
|
||||
"\n",
|
||||
"ui.launch()"
|
||||
"ui.launch(inbrowser=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b0b12548-951d-4e7c-8e77-803a92271855",
|
||||
"cell_type": "markdown",
|
||||
"id": "226643d2-73e4-4252-935d-86b8019e278a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
"source": [
|
||||
"# Business Applications\n",
|
||||
"\n",
|
||||
"Add in more tools - perhaps to simulate actually booking a flight. A student has done this and provided their example in the community contributions folder.\n",
|
||||
"\n",
|
||||
"Next: take this and apply it to your business. Make a multi-modal AI assistant with tools that could carry out an activity for your work. A customer support assistant? New employee onboarding assistant? So many possibilities!\n",
|
||||
"\n",
|
||||
"If you feel bold, see if you can add audio input to our assistant so you can talk to it. "
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
Reference in New Issue
Block a user