2024-03-25: GPT-4 environment variables

You can now specify your GPT model name and version entirely in the azd environment variables. See updated documentation here:
https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/docs/deploy_features.md#using-gpt-4

What's Changed

• Fix search secret name environment variable for free deploys by @pamelafox in #1455
• Allow manual setting of the OpenAI Deployment Name, Version, Capacity and Model by @john0isaac in #1386

Full Changelog: 2024-03-20...2024-03-25

2024-03-20: New settings for minimum search score for search results

This release includes a new feature to restrict the search results based on the minimum score, via a new option in Developer Settings and new POST parameters. You can learn more about search scoring here:
https://learn.microsoft.com/azure/search/hybrid-search-ranking#scores-in-a-hybrid-search-results
You may want to experiment with scoring thresholds if you find that the search results are not always relevant. Reminder that you can use the evaluator tools to see differences in app settings:
https://github.com/Azure-Samples/ai-rag-chat-evaluator

What's Changed

• Update chatreadretrieveread.py (Typo "Azure Open AI"→"Azure OpenAI") by @hyoshioka0128 in #1443
• Update retrievethenread.py (Typo "Azure Open AI"→"Azure OpenAI") by @hyoshioka0128 in #1447
• Bump the github-actions group with 1 update by @dependabot in #1439
• Add minimum score criteria for AI search results by @sogue in #1417

Full Changelog: 2024-03-18...2024-03-20

2024-03-18: Markdown viewer

The code change in this release is the addition of a Markdown viewer, so that users can click on a cited markdown file and see it formatted in the browser.

What's Changed

• Add Markdown File Viewer by @yuvalyaron in #1384
• Added an instruction to Compile the JavaScript, required for pytest to pass. by @giterinhub in #1425
• Update other_samples.md to reflect current features/tech by @pamelafox in #1388
• Update approach.py (Typo "Azure Open AI"→"Azure OpenAI") by @hyoshioka0128 in #1431
• Fix links in documentation by @pamelafox in #1426
• Update gpt4v.md (Typo "Azure Open AI models"→"Azure OpenAI models") by @hyoshioka0128 in #1435

New Contributors

• @giterinhub made their first contribution in #1425

Full Changelog: 2024-03-14...2024-03-18

2024-03-14: AZURE_OPENAI_API_VERSION, bug fixes

This new release includes the ability customize the OpenAI API version via an environment variable (AZURE_OPENAI_API_VERSION) and also updates the version to the latest preview, 2024-03-01-preview. This release also includes an important bugfix in the prepdocs script, so please pull in that fix if you're getting errors with computing embeddings.

What's Changed

• Fix provision for load balance custom by @diberry in #1396
• Update data_ingestion.md with correct notebook link by @pamelafox in #1405
• Bump the github-actions group with 1 update by @dependabot in #1400
• Add needed permissions for template-analyzer workflow by @pamelafox in #1411
• Set Azure OpenAI API version in global configuration by @sogue in #1399
• Add markdown checker by @john0isaac in #1377
• Refactoring of prepdocs for easier integration with user upload feature by @pamelafox in #1407
• Don't disable text chunking when GPT4vision is enabled by @pamelafox in #1355
• Ensure there are no zero-length sections for batch API by @tonybaloney in #1423

New Contributors

• @sogue made their first contribution in #1399

Full Changelog: 2024-03-07...2024-03-14

2024-03-07: Text parser, "Thought process" enhancements

This release includes a simple local parser for text files (including markdown), as well as enhancements to the "Thought process" tab to show additional details about the answer flow, like search results scores and models/deployments used. We aim to add a "score threshold" in the future so that you can filter out results with too low of a score.

What's Changed

• Add search scores, models, and deployments to "Thought process" tab, surface additional properties by @pamelafox in #1375
• Add Markdown/Text Parser by @yuvalyaron in #1381

New Contributors

• @yuvalyaron made their first contribution in #1381

Full Changelog: 2024-03-06...2024-03-07

2024-03-06: Token-based text splitting for data ingestion

The highlight of this release is a new token-based text splitter, used by the prepdocs script when splitting content into chunks for the search index. The previous algorithm was based solely on character count, which meant that our prepdocs script did not work well for non-English documents or any documents which resulted in a higher than usual amount of tokens. If you do experience any regression in splitting quality as a result of this change, please file an issue.

What's Changed

• Improve text splitter for non-English documents by @tonybaloney in #1326
• Restrict GitHub workflows run by @john0isaac in #1366
• Improvements to load balancer setup script by @pamelafox in #1348
• Update productionizing.md with link to search service size guide by @pamelafox in #1354
• Update README.md to delete old links by @pamelafox in #1372
• Update deploy_features.md link by @pamelafox in #1373
• Add suggestion to use [azd auth login] in the free low-cost deploy tutorial by @elbruno in #1214
• Bump the python-requirements group with 18 updates by @dependabot in #1368

New Contributors

• @elbruno made their first contribution in #1214

Full Changelog: 2024-03-01...2024-03-06

2024-03-01: Local HTML parser

This release adds the option of using a local HTML parser instead of Azure Document Intelligence, for developers who want to reduce costs or have more flexibility in the HTML parsing. See the docs for information on enabling the parser.

What's Changed

• Readme refactor by @pamelafox in #1346
• feat: add local html parser by @john0isaac in #1351

New Contributors

• @john0isaac made their first contribution in #1351

Full Changelog: 2024-02-28...2024-03-01

2024-02-28: OpenTelemetry instrumentation for OpenAI calls

The primary change in this release is the integration of the opentelemetry-instrumentation-openai package for tracing OpenAI calls. You should now see traces for all calls made by the OpenAI SDK in Azure Monitor.

We are still using the HTTPX instrumentation package as well, which should also trace the calls since OpenAI SDK uses HTTPX for HTTP calls behind the scenes, but they recently made a change that's resulting in inconsistent HTTPX tracing. You may sometimes see multiple traces for same call, one from the HTTPX instrumentor and one from the new OpenAI instrumentor.

What's Changed

• Implement better LLM tracing with llmetry OpenAI instrumentation by @tonybaloney in #1319
• Improve PR template to reference tutorial changes and contributing checklist by @pamelafox in #1335
• Update launch.json with python backend path by @pamelafox in #1022
• Update app diagram by @pamelafox in #1338
• Show users a special message for context length errors by @pamelafox in #1337

Full Changelog: 2024-02-27...2024-02-28

2024-02-27: HTML parsing via Azure Document Intelligence

We updated prepdocs.py so that HTML files will be processed by Azure Document Intelligence. Here's a stream demonstrating ingestion of HTML docs. You can just update to latest, put HTML files in the data/ folder, and they will get picked up.

What's Changed

• Add HTML parsing via Azure Document Intelligence by @pamelafox in #1325

Full Changelog: 2024-02-23...2024-02-27

2024-02-23: AAD for Computer Vision API, Load balancer script

This release updates our Python dependencies, switches to using AAD for authenticating to the Computer Vision API, and adds a script for easier integration with the ContainerApps-based OpenAI load balancer.

If you are using the GPT-4-vision, then you should run "azd provision" to get the new roles needed to authenticate to the Computer Vision API.

What's Changed

• Add setup script for setting up ACA loadbalancer by @diberry in #1310
• Use AAD instead of key vault for Computer Vision API by @pamelafox in #1062
• Bump the github-actions group with 1 update by @dependabot in #1290
• Bump the python-requirements group with 10 updates by @dependabot in #1291

Full Changelog: 2024-02-16...2024-02-23