Gencore AI for Alibaba Cloud OSS

Gencore AI helps organizations rapidly build secure, enterprise-grade generative AI systems, copilots, and agents using their proprietary data. It simplifies GenAI adoption by enabling the creation of structured and unstructured data pipelines that integrate enterprise data from hundreds of systems and applications.

The platform supports any foundation model available on Google Cloud, including Vertex AI, Gemini, and PaLM 2, as well as third-party models such as Anthropic Claude, Meta Llama 2, and Mistral.

Key Capabilities

1. Build Secure Enterprise AI Copilots
   Quickly create AI copilots and knowledge systems by combining data from multiple sources, with built-in enterprise controls, AI usage monitoring, and end-to-end provenance tracking.

2. Secure Data Sync to Vector Databases
   Ingest and synchronize enterprise data at scale, generating custom embeddings with rich metadata to prepare data for LLM consumption.

3. Curate and Sanitize Training Data
   Assemble, clean, and sanitize high-quality datasets for AI model training and fine-tuning with ease.

4. Protect AI Interactions
   Use a conversation-aware LLM Firewall to safeguard prompts, responses, and data retrievals, enforcing enterprise policies and preventing threats such as prompt injection, data leakage, and jailbreak attempts.

Key Features

1. Enterprise-Wide Data Connectivity
   Safely ingest data using hundreds of native connectors across SaaS, on-premises, public cloud, and data cloud environments.

2. Inline Security Across the AI Pipeline
   Apply layered protections including data sanitization, policy-enforced LLM firewalls, and continuous compliance monitoring aligned with standards such as NIST AI RMF and the EU AI Act.

3. End-to-End AI System Visibility
   Gain complete transparency into AI usage, data flows, users, files, and model endpoints with full system provenance.

Loading Microsoft 365 OneDrive Data

To build your GenAI pipeline with Microsoft 365 OneDrive data in minutes:

1. Select Microsoft 365 OneDrive as the data source.

2. Choose the relevant system, bucket, or attributes.

3. Define the data scope.

4. Apply optional filters such as object name, tags, size, extension, or last modified date.

5. Click Save and Continue to proceed to the Data Sanitizer stage.