Gencore AI for SFTP

Gencore AI helps organizations rapidly and securely build enterprise-grade generative AI (GenAI) systems, AI copilots, and intelligent agents. It streamlines GenAI adoption by enabling the creation of AI pipelines that combine structured and unstructured data from proprietary enterprise sources across hundreds of systems and applications.

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

Core Capabilities:

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

2. Securely Sync Data to Vector Databases: Ingest and synchronize data at scale, generate custom embeddings with metadata, and prepare enterprise data for LLM usage.

3. Curate and Clean Data for Training: Assemble, sanitize, and prepare high-quality datasets for AI model training and fine-tuning.

4. Protect AI Interactions: The conversation-aware LLM Firewall safeguards prompts, responses, and data retrievals, preventing sensitive data leaks and mitigating risks like prompt injections or jailbreak attempts.

Key Features:

1. Enterprise-Wide Data Connectivity: Seamlessly ingest data through hundreds of native connectors, supporting unstructured and structured data across SaaS, on-premise, public, and cloud environments.

2. Comprehensive AI Pipeline Controls: Enforce data sanitization, policy-compliant AI interactions, and continuous compliance monitoring (e.g., NIST AI RMF, EU AI Act).

3. Full AI System Provenance: Track every AI action and data point across files, users, models, and endpoints for complete visibility.

Loading Your SFTP Data for GenAI Pipelines:

1. Select SFTP as the source.

2. Specify the data system, bucket, or relevant SFTP attribute.

3. Define the scope for your SFTP data.

4. Optionally filter data by:

   • Object Prefix (text or regex)

   • Object Name (regex)

   • Object Tags (key:value)

   • Object Extension Category

   • Object Extensions

   • Object Size

   • Last Modified date

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