Orbit Platform Documentation
DocsAPI ReferenceHomepageSign In
Documentation
Documentation
  • Welcome
  • 1. Introduction
    • 1.1 Orbit Platform Overview
    • 1.2 Key Features
    • 1.3 Target Audience
    • 1.4 Benefits of Using Orbit Platform
    • 1.5 Overview of this Documentation
  • 2. Quick Start
    • 2.1 Accessing Orbit Platform
    • 2.2 Navigating the User Interface
    • 2.3 Basic User Cases
      • 2.3.1 Conducting a Semantic Search
      • 2.3.2 Copilot Chat
      • 2.3.3 Browsing and Using Pre-Defined Bots
    • 2.4 Exploring the Bot Marketplace
    • 2.5 Understanding SaaS Features and Limitations
  • 3. Platform Overview
    • 3.1 Overview of Orbit Platform
    • 3.2 Orbit AI Studio
      • 3.2.1 Data Loaders
      • 3.2.2 Metadata Management
      • 3.2.3 PDF Pre-Processing
      • 3.2.4 LLM Integration
      • 3.2.5 Workflow Automation
    • 3.3 Custom Knowledge Base Creation
    • 3.4 Chat and Search Capabilities
    • 3.5 Bot Marketplace
      • 3.5.1 Overview of the Bot Marketplace
      • 3.5.2 Creating and Managing Bots
      • 3.5.3 Automating Manual Tasks with Bots
  • 3.6 Data Connectors
  • 4. User Guide
    • 4.1 General User Interface
      • 4.1.1 Portfolio Management
      • 4.1.2 Concept Management
      • 4.1.3 Share
    • 4.2 Semantic Search and Chat
    • 4.3 Features on Single Document
    • 4.4 Create Your Knowledge Base
  • 5. Orbit Knowledge Bases
    • 5.1 Introduction
  • 5.2 Global Exchange Filings
  • 5.3 China Earnings Transcripts
  • 5.4 Global Sustainability Reports
  • 5.5 Global Regulation Documents
  • 5.6 Global Earnings Transcripts
  • 5.7 Listed Companies Official Documents
  • 5.8 Private Companies Official Documents
  • 5.9 Google News
  • 5.10 China Bond Documents
  • 6. Off-the-Shelf Bots
    • 6.1 Data Transformer
    • 6.2 Filings Insight Extractor
    • 6.3 Portfolio News Tracker
    • 6.4 Summary Composer
    • 6.5 Financial Statement Navigator
    • 6.6 Earning Call Calendar
    • 6.7 News Flow Tracker
  • 6.8 SmartMonitor Bot
  • 7. Pricing
    • 7.1 Product Options
    • 7.2 SaaS Pricing Structure
  • 7.3 Product Selection Guide
  • 8. Enterprise Deployment
    • 8.1 Deployment Options
    • 8.2 Security and Compliance
    • 8.3 Scaling and Performance
    • 8.4 Integration with Existing Systems
  • 9. Use Cases and Examples
    • 9.1 Investment Research Use Cases
      • 9.1.1 Generate a Research Report with Copilot Chat
      • 9.1.2 Analyse Investment Themes from Annual Reports
    • 9.2 Sustainability Use Cases
      • 9.2.1 Generate an ESG Report with Copilot Chat
      • 9.2.2 Orbit vs Claude vs Perplexity
    • 9.3 Service Provider Use Cases
    • 9.4 Case Studies: Success Stories
  • 10. FAQ and Troubleshooting
    • 10.1 Common Questions
    • 10.2 Contacting Support
  • 11. Appendices
    • 11.1 Glossary of Terms
    • 11.2 Whitepapers
      • Advancing News Analytics for Financial Decision Making
    • 11.3 Release Notes
Powered by GitBook
On this page

While having an intelligent system like Orbit AI Studio is crucial for advanced data processing and analysis, the true power of the platform is unlocked when it is paired with the right content. For financial research and similar use cases, this means having access to vast volumes of high-quality, curated data that is ready for immediate use by Large Language Models (LLMs). Recognizing this need, Orbit Insight comes pre-loaded with carefully curated datasets, allowing users to start their research from day one.

The Challenge of Data Availability

In data-driven industries such as finance, the availability of high-quality data is often a significant challenge. Even the most sophisticated AI systems require vast amounts of data to function effectively, particularly when using LLMs for tasks like natural language processing, semantic search, and advanced analytics. Simply having access to data is not enough—the data must be relevant, comprehensive, and structured in a way that enables meaningful analysis.

  • Data Volume and Relevance: LLMs thrive on large datasets that cover a wide range of relevant topics. However, sourcing, organizing, and maintaining such datasets is a complex task that can be both time-consuming and resource-intensive.

  • Data Structure: For LLMs to perform optimally, the data needs to be structured and formatted correctly. This includes having accurate metadata, clean text, and logical organization that aligns with the intended use cases.

Carefully Curated Datasets

To address these challenges, Orbit Insight comes pre-loaded with a variety of carefully curated datasets. These datasets have been selected and organized to ensure that users can immediately begin conducting meaningful research without the need for extensive data preparation.

  • Pre-Loaded Content: Upon deployment, Orbit Insight provides access to extensive datasets that are ready for immediate use. These pre-built knowledge bases cover a broad spectrum of topics relevant to financial research, including market data, financial reports, regulatory information, and more.

  • Research-Ready from Day One: With these pre-built knowledge bases, users can start conducting research and analysis from the moment they access the platform. This eliminates the initial time lag typically associated with data preparation and allows users to quickly generate insights and make informed decisions.

  • Continuous Updates: The pre-built knowledge bases are not static; they are continuously updated to ensure that the data remains current and relevant. This ongoing maintenance ensures that users always have access to the latest information, which is crucial for making timely and accurate decisions.

Last updated 1 month ago

  1. 5. Orbit Knowledge Bases

5.1 Introduction

Previous4.4 Create Your Knowledge BaseNext5.2 Global Exchange Filings
  • The Challenge of Data Availability
  • Carefully Curated Datasets