Gencore AI for Go File Room

Gencore AI helps companies rapidly and safely develop enterprise-grade generative AI (GenAI) systems, AI copilots, and intelligent agents. It speeds up GenAI adoption by simplifying the creation of AI pipelines that handle both structured and unstructured data across hundreds of enterprise systems and applications.

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

Core Capabilities:

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

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

3. Prepare Data for Model Training: Assemble, cleanse, and sanitize high-quality datasets efficiently for AI model training and tuning.

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

Key Features:

1. Comprehensive Enterprise Data Connectivity: Ingest data through hundreds of native connectors and support AI applications that work with structured and unstructured data across SaaS, on-premise, public, and cloud environments.

2. Inline AI Pipeline Controls: Ensure AI operations comply with policies via data sanitization before model consumption, LLM firewalls, and continuous compliance monitoring (NIST AI RMF, EU AI Act, etc.).

3. Full AI System Transparency: Monitor the complete AI system, including data usage and AI interactions down to individual files, users, and model endpoints.

Steps to Load Go File Room Data for Your GenAI Pipeline:

1. Choose Go File Room as the data source.

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

3. Define the scope for Go File Room data.

4. Apply optional filters:

   • Object Prefix (text or regex)

   • Object Name (regex)

   • Object Tags (key:value pairs)

   • Extension Category

   • Extensions

   • Object Size

   • Last Modified Date

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