Gencore AI for Azure Files

Gencore AI allows organizations to quickly and easily build secure, enterprise-grade generative AI (GenAI) systems, AI copilots, and intelligent agents. It speeds up enterprise GenAI adoption by simplifying the creation of pipelines that combine structured and unstructured proprietary data across hundreds of diverse systems and applications.

You can leverage any foundation model available in Google Cloud, including Vertex AI, Gemini, and PaLM 2, as well as third-party models like Anthropic Claude, Meta Llama 2, and Mistral.

Core Capabilities:

1. Create Secure Enterprise AI Copilots: Build AI copilots and knowledge systems by integrating data from multiple sources in minutes, with automatic enterprise controls, AI usage tracking, and full provenance.

2. Safely Sync Data to Vector Databases: Ingest and synchronize data securely at scale, generate custom embeddings with metadata for vector databases, and prepare enterprise data for LLM use.

3. Curate and Sanitize Training Data: Easily assemble, clean, and sanitize high-quality datasets for AI model training and fine-tuning.

4. Protect AI Interactions: The conversation-aware LLM Firewall safeguards user prompts, AI responses, and data retrievals, ensuring secure and policy-compliant interactions.

Key Features:

1. Enterprise-Wide Data Connectivity: Safely ingest data via hundreds of native connectors and enable AI applications that leverage both structured and unstructured data across SaaS, on-premises, public, and cloud environments.

2. Inline AI Pipeline Controls: Ensure secure AI operations with layers including pre-processing data sanitization, LLM firewalls for policy compliance, and ongoing compliance monitoring (NIST AI RMF, EU AI Act, etc.).

3. Full AI System Provenance: Achieve complete visibility of your AI systems, including all data and AI usage at the file, user, and model levels.

For support, visit Securiti Contact.

Steps to Load Azure Files Data into Your GenAI Pipeline in Minutes:

1. Choose Azure Files as the source.

2. Select the appropriate data system, bucket, or attribute for Azure Files.

3. Define the scope for Azure Files data.

4. Apply optional filters:

   • Object Prefix: Text or regex prefix to match.

   • Object Name: Match based on regex.

   • Object Tags: Key-value tag filtering.

   • Extension Category / Extensions: Filter by file type or extension.

   • Object Size: Filter by size.

   • Last Modified: Filter by modification date.

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