| Knowledge Mining with Azure OpenAI |
Deployment of a Python-based Knowledge Mining solution with OpenAI that will ingest a Knowledge Base, generate embeddings using the contents extracted, store them in a vector search engine (Redis), and use that engine to answer queries / questions specific to that Knowledge Base. |
Azure OpenAI; LangChain; Cognitive Search, Vector Store |
Automotive, Banking, Energy, Media |
Link |
Productivity, Knowledge Finding |
Solution Architects |
Material |
Link |
| Dynamics 365 Sales Acceleration |
Eine Demo, die zeigt, wie Vertriebsteams ihre Verkaufsprozesse mit KI beschleunigen können, indem sie die neuesten Tools und Funktionen von Dynamics 365 Sales nutzen. |
Dynamics 365 Sales, Künstliche Intelligenz, Datenanalyse |
B2B / kein Industrie-Fokus |
Reference |
Verkürzung des Verkaufszyklus, Erhöhung der Lead-Konversionsrate, Steigerung der Verkaufseffizienz |
Geschäftsleitung, Vertriebsleiter, Vertriebsmitarbeiter |
Klick-Demo |
Link |
| OpenAI workshop |
Workshop materials to build intelligent solutions on Open AI |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |
| Semantic Kernel |
Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages. |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |
| Visual ChatGPT |
Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |
| Athena - Generate Synapse queries with Azure OpenAI |
We know that LLMs can generate SQL code from Natural language. The challenge in adopting this to empower all skill levels to query big data is many fold. From LLM perspective: For a correct SQL query generation from natural langugae, LLMs not only need to understad the context but also have an understanding of the database schema. Passing schema to prompts could be an approach here but this is not scalable. In this repo we showcase using prompt engineering approaches from chain of thought modelling we can make this approach scalable. This project shows LLMs working from natural language to query a star schema in data lake (via Synapse) without the need to know the DB schema before hand. |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |
| Azure OpenAI Embeddings QnA |
A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3 to extract the matching answer for the question. |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |
| Azure OpenAI Example Prompts |
This repository shares example code and example prompts for accomplishing common tasks with the Azure OpenAI API. |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |
| Azure OpenAI integration with Azure Cognitive-Search for document analysis |
Azure OpenAI integration as a custom skillset in Azure Cognitive Search |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |
| Azure Cognitive Semantic Search with OpenAI enrichment |
Azure Cognitive Semantic Search that works on large documents, with OpenAI enrichment. |
Technologies |
Industries |
Reference |
KPIs |
Audience |
Material |
Link |