feat: Ai foundry#2398
Merged
Merged
Conversation
Contributor
Author
|
/azp run |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #2398 +/- ##
==========================================
+ Coverage 84.47% 84.49% +0.02%
==========================================
Files 331 332 +1
Lines 17217 17242 +25
Branches 1541 1547 +6
==========================================
+ Hits 14544 14569 +25
Misses 2673 2673 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Contributor
Author
|
/azp run |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Contributor
Author
|
/azp run |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Contributor
Author
| @@ -0,0 +1 @@ | |||
| {"cells":[{"cell_type":"markdown","source":["# Chat Completion with Azure AI Foundry model\n","\n","[Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-azure-ai-foundry) enables the execution of a wide range of natural language tasks using the Completion API. Its integration with SynapseML simplifies leveraging the Apache Spark distributed computing framework to handle large volumes of prompts across various models, including those from Deepseek, Meta, Microsoft, xAI, and others. For a full list of [supported models](https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models), refer to Azure AI Foundry documentation.\n","Note: To use OpenAI models, integration is available through the OpenAIChatCompletion class. Refer to the relevant documentation for details on [using OpenAI models](https://microsoft.github.io/SynapseML/docs/Explore%20Algorithms/OpenAI/).\n"],"metadata":{"nteract":{"transient":{"deleting":false}}},"id":"6b268f55-cda1-49c1-ae84-0d6f38d0946a"},{"cell_type":"markdown","source":["## Prerequisites\n","The key prerequisites for this quickstart include \n","\n","- An [Azure subscription](https://azure.microsoft.com/en-us/pricing/purchase-options/azure-account)\n","\n","- A working Azure AI Foundry project resource and a model deployed\n"," * Sign in to the [Azure AI foundry portal](https://ai.azure.com/)\n"," * Select a chat completion model. We use Phi-4-mini-instruct model as an example. \n"," * \n","\n"," \n"," * On the model details page, select Use this model.\n"," * Fill in a name to use for your project and select Create.\n","\n","- An Apache Spark cluster with SynapseML installed."],"metadata":{"nteract":{"transient":{"deleting":false}}},"id":"3f705336-0fd0-4b08-930a-1c5f7aa684de"},{"cell_type":"markdown","source":["# Fill in service information\n","Next, edit the cell in the notebook to point to your service. \n","\n","In particular set the service_name, api_version to match them to your AI Foundry model.\n","To get your service_name, api_version and api_key, Select My Asset, Find Target URI. API version is also in target URI.\n","\n","\n"],"metadata":{"nteract":{"transient":{"deleting":false}}},"id":"75ad6753-02ee-4190-b993-4825a76d5f07"},{"cell_type":"code","source":["from synapse.ml.core.platform import find_secret\n","\n","# Fill in the following lines with your service information\n","service_name = \"synapseml-ai-foundry-resource\"\n","api_verion = \"2024-05-01-preview\"\n","model = \"Phi-4-mini-instruct\"\n","api_key = find_secret(\n"," secret_name=\"synapseml-ai-foundry-resource-key\", keyvault=\"mmlspark-build-keys\"\n",") # please replace this line with your key as a string\n","\n","assert api_key is not None and service_name is not None"],"outputs":[],"execution_count":null,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"d65e5ef6-dc64-44e4-ae59-10ed8d8c1811"},{"cell_type":"markdown","source":["## Chat Completion\n","\n","Models such as Phi-4 and llama are capable of understanding chats instead of single prompts. The `AIFoundryChatCompletion` transformer exposes this functionality at scale."],"metadata":{"nteract":{"transient":{"deleting":false}},"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"886323f0-22c9-49c9-9c26-ca164c273c04"},{"cell_type":"code","source":["from synapse.ml.services.aifoundry import AIFoundryChatCompletion\n","from pyspark.sql import Row\n","from pyspark.sql.types import *\n","\n","\n","def make_message(role, content):\n"," return Row(role=role, content=content, name=role)\n","\n","\n","chat_df = spark.createDataFrame(\n"," [\n"," (\n"," [\n"," make_message(\n"," \"system\", \"You are an AI chatbot with red as your favorite color\"\n"," ),\n"," make_message(\"user\", \"Whats your favorite color\"),\n"," ],\n"," ),\n"," (\n"," [\n"," make_message(\"system\", \"You are very excited\"),\n"," make_message(\"user\", \"How are you today\"),\n"," ],\n"," ),\n"," ]\n",").toDF(\"messages\")\n","\n","\n","chat_completion = (\n"," AIFoundryChatCompletion()\n"," .setSubscriptionKey(api_key)\n"," .setCustomServiceName(service_name)\n"," .setModel(model)\n"," .setApiVersion(\"2024-05-01-preview\")\n"," .setMessagesCol(\"messages\")\n"," .setErrorCol(\"error\")\n"," .setOutputCol(\"chat_completions\")\n",")\n","\n","display(\n"," chat_completion.transform(chat_df).select(\n"," \"messages\", \"chat_completions.choices.message.content\"\n"," )\n",")"],"outputs":[],"execution_count":null,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"},"collapsed":false},"id":"d4491222-78c6-4136-8711-8f837915b2a9"}],"metadata":{"language_info":{"name":"python"},"kernel_info":{"name":"synapse_pyspark"},"kernelspec":{"display_name":"synapse_pyspark","language":null,"name":"synapse_pyspark"},"a365ComputeOptions":null,"sessionKeepAliveTimeout":0,"microsoft":{"language":"python","language_group":"synapse_pyspark","ms_spell_check":{"ms_spell_check_language":"en"}},"nteract":{"version":"nteract-front-end@1.0.0"},"spark_compute":{"compute_id":"/trident/default","session_options":{"conf":{"spark.synapse.nbs.session.timeout":"1200000"}}},"synapse_widget":{"version":"0.1","state":{}},"dependencies":{"lakehouse":null}},"nbformat":4,"nbformat_minor":5} No newline at end of file | |||
Contributor
There was a problem hiding this comment.
if we can format this so its multiline that will make it a bit easier to comment on
Contributor
Author
|
/azp run |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Contributor
Author
|
/azp run |
|
Azure Pipelines successfully started running 1 pipeline(s). |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.