Gencore AI for OpenText Content Server

Gencore AI helps enterprises rapidly build secure, production-ready generative AI systems, copilots, and AI agents. It simplifies GenAI adoption by enabling fast creation of AI pipelines for both structured and unstructured data, leveraging proprietary enterprise data from hundreds of diverse data sources and applications.

Organizations can use any foundation model available on Google Cloud—such as Vertex AI, Gemini, and PaLM 2—as well as leading third-party models including 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 enterprise platforms. Built-in governance includes automatic controls, AI usage monitoring, and complete provenance tracking.

2. Safely Sync Data to Vector Databases
   Securely ingest and synchronize large volumes of data from multiple systems. Generate custom embeddings with metadata to prepare enterprise data for LLM-based applications.

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

4. Protect AI Interactions
   Use a conversation-aware LLM Firewall to safeguard user prompts, model responses, and data retrieval within AI workflows.

Key Features

• Enterprise-Wide Data Connectivity
  Ingest data securely using hundreds of native connectors, supporting AI use cases across SaaS platforms, on-prem environments, public clouds, and data clouds.

• Inline Security and Compliance Controls
  Apply layered protections throughout the AI pipeline, including data sanitization before model consumption, policy-enforcing LLM firewalls, and continuous compliance monitoring aligned with frameworks such as NIST AI RMF and the EU AI Act.

• End-to-End AI System Visibility
  Achieve full transparency across data and AI usage, with detailed tracking down to individual files, users, models, and inference endpoints.

Loading OpenText Content Server Data for GenAI Pipelines

Building a GenAI pipeline with OpenText Content Server data can be done in minutes:

1. Choose OpenText Content Server as the data source.

2. Select the specific data system, bucket, or relevant attribute.

3. Define the scope of data to be ingested.

4. Optionally apply filters such as object prefix, name, tags, file type, size, or last modified date.

5. Save and continue to the Data Sanitizer stage to prepare data for secure AI usage.

For support, users can contact the Gencore AI team directly through their support channel.