> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bigdata.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

The Bigdata API gives developers five ways to integrate knowledge into their applications:

* **Research Agent** - a conversational endpoint for reasoning and analysis.
* **Workflows API** - templated, reproducible research for automation.
* **Search Service** - a retrieval-only endpoint for fast, precise document access.
* **Content API** - ingest and manage private documents so they can be searched and analyzed alongside Bigdata's corpus.
* **Monitors API** <Badge color="blue" size="sm" shape="pill">Coming soon</Badge> - recurring searches that produce structured events from new content.

Together, they combine information retrieval with generative AI, enabling applications to deliver accurate, context-aware responses grounded in real-time data and trusted knowledge sources.

# Research Agent

The Research Agent Service is designed for **conversational intelligence**. It supports multi-turn dialogue, letting users refine queries or ask follow-ups. Built on **retrieval-augmented generation (RAG)**, it merges an LLM framework with search across the web, premium sources, and your own content.

* **What it delivers:** Synthesized, context-rich answers that show reasoning, summarization, and insight.

* **Best for:** Business and financial research, complex analysis, decision support.

# Workflows API

The Workflows API enables **templated, reproducible research** designed for automation. Unlike the conversational Research Agent, Workflows uses parameterized templates that produce consistent outputs.

* **What it delivers:** Reproducible, structured research reports from reusable templates.
* **Best for:** Batch processing, scheduled reports, consistent analysis across entities.

# Search Service

The Search Service is a **retrieval-only API** that indexes both structured and unstructured data. Unlike the Research Agent, it does not interpret or summarize content, it simply returns the most relevant documents or snippets.

* **What it delivers:** Raw but precise results, optimized for low latency and high recall.
* **Best for:**
  * Grounding LLMs with factual context
  * Populating context windows
  * Powering standalone search tools
  * Supplying downstream agents with curated source material

# Content API

The Content API is how you **bring proprietary knowledge into Bigdata**. Upload files yourself, or ingest them through connectors such as an email inbox, broker investment research feeds, or SharePoint. Each document is enriched and indexed, so Search and Research Agent can use it as a first-class source.

* **What it delivers:** Private, tagged documents you can list, filter, and retrieve as annotated JSON or original files.
* **Best for:** Internal reports, newsletters, broker notes, and SharePoint libraries you want searchable alongside Bigdata's corpus; questions that span private material and market data.
* **Learn more:** [Upload your own content](/getting-started/upload_your_own_content) and the [Content API introduction](/api-rest/content_introduction).

# Monitors API <Badge color="blue" size="sm" shape="pill">Coming soon</Badge>

The Monitors API turns a saved search into a continuous feed. It searches newly available content on a schedule and extracts structured, source-backed events.

* **What it delivers:** Repeatable events from new content, with structured fields and links to supporting sources.
* **Best for:** Credit surveillance, M\&A tracking, policy decisions, leadership changes, and other developments that require continuous coverage.
* **Learn more:** Preview the workflow in [Get started with Monitors](/getting-started/monitors/overview).

# FAQ

<AccordionGroup>
  <Accordion title="What is the difference between Search and Research Agent Services?">
    The [Research Agent](../api-reference/research-agent) is a model endpoint designed for conversational intelligence. It supports multi-turn dialogue, allowing users to ask follow-up questions and refine their queries. Built on real-time retrieval-augmented generation (RAG), it combines an LLM framework with search capabilities across proprietary, premium, and web content sources.

    The result is a synthesized, context-aware response that reflects reasoning, summarization, and insight generation, ideal for business/financial analysis and complex decision support.

    In contrast, the [Search Service](../getting-started/quickstart_guide) is a retrieval-only API. It indexes structured and unstructured data to return the most relevant documents or snippets, without interpretation or synthesis. It's optimized for low latency and high precision, making it ideal for tasks such as grounding LLMs, populating context windows, powering search tools, or feeding downstream agents with raw but relevant content.

    <Tip>
      * Research Agent = LLM + RAG → contextual, reasoned answers.
      * Search = fast, relevant retrieval → raw source material.
    </Tip>
  </Accordion>

  <Accordion title="What is the difference between Fast and Smart Search modes?">
    Fast mode gives you full control over all filters for precise, deterministic, low-latency results. Smart mode handles query understanding for you, automatically inferring intent, applying filters, and running sub-queries for broader coverage. Ideal for natural-language questions without pre-processing. Higher latency than Fast mode.

    | **Request Parameter** | **Fast Mode** | **Smart Mode** |
    | :- | :- | :- |
    | Text | ✅ | ✅\* |
    | Temporal filter | ✅ Manual or Partially Automated | ✅ Manual or Fully Automated |
    | Source filter | ✅ | ✅ Manual or Fully Automated |
    | Reporting date filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Document type filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Entity filter | ✅ Manual or Partially Automated | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Reporting entity filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Keyword filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Tag filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Sentiment filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Author filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Speaker filter | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Ranking parameters | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | Content Diversification | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated |
    | External Search | ✅ | <Icon icon="sparkles" size={16} /> Fully Automated (if enabled)\*\* |

    \* [`texts`](/api-reference/search/search-documents#body-query-texts) (multiple natural-language search strings) is only available in Fast mode. In Smart mode, send a single `text` and the system runs its own sub-queries to broaden coverage.

    \*\* You opt-in by setting [`external_search`](/api-reference/search/search-documents#body-query-external-search) with mode `INCLUDE` and any of the supported values (e.g., `web`). Smart Mode then decides whether to call external search based on query intent. If it determines external search isn't needed, no additional cost is incurred. This approach ensures you only pay for external search when it's actually used.
  </Accordion>

  <Accordion title="How does the Content API relate to Search and Research Agent?">
    The [Content API](/api-rest/content_introduction) is the ingestion and management layer for private documents. You onboard content through **connectors** (email, investment research, SharePoint) or **direct upload**.

    Bigdata enriches and indexes each file, so that [Search](/getting-started/quickstart_guide) and [Research Agent](/getting-started/quickstart_guide_research_agent) become the retrieval and reasoning layers. They query both Bigdata's corpus and your indexed documents.
  </Accordion>
</AccordionGroup>

# Quickstart Guides

<CardGroup cols={1}>
  <Card title="Research Agent" icon="messages" horizontal="True" href="/getting-started/quickstart_guide_research_agent">
    Create intelligent assistants that combine web and premium data with your proprietary content for deeper insights and productivity.
  </Card>

  <Card title="Workflows API" icon="diagram-project" horizontal="True" href="/getting-started/quickstart_guide_workflows">
    Build reproducible, templated research workflows for automated analysis.
  </Card>

  <Card title="Search Service" icon="magnifying-glass" horizontal="True" href="/getting-started/quickstart_guide">
    Easily find the most relevant information from trusted sources and your own data. Use it to power agents that give accurate, real-time answers.
  </Card>

  <Card title="Content API" icon="file-lines" horizontal="True" href="/api-rest/content_introduction">
    Upload files or ingest them through connectors. Enrich and index private documents so Search and Research Agent can use them.
  </Card>

  <Card title={<span className="flex items-center gap-2">Monitors API <Badge color="blue" size="sm" shape="pill">Coming soon</Badge></span>} icon="radar" horizontal="True" href="/getting-started/monitors/overview">
    Run a saved search continuously and receive structured events when new developments appear.
  </Card>
</CardGroup>

<Tip>
  For more in-depth, practical examples that build your confidence with specific service features, explore the [How-to guides](../how-to-guides/introduction) section. If you're interested in real financial use cases that deliver customer value, check out the [Cookbooks](../use-cases/introduction) section.
</Tip>

# Bigdata Developer Platform

We recommend using the [Developer Platform](https://platform.bigdata.com) to test your queries and understand how our APIs work.

Also, use it to manage your API keys and monitor your API consumption and costs.

<Card title="🚀 Bigdata Developer Platform" href="https://platform.bigdata.com">
  **Your companion for day-to-day Bigdata API development**

  The Developer Platform is your central hub for managing, testing, and optimizing your Bigdata API integrations. Get instant business value with interactive playgrounds that make it incredibly easy to understand how our APIs work and discover their full potential.

  **Key Features:**

  * **🎮 Advanced Playgrounds**: Interactive environments with visual input/output to experiment with queries and see results instantly
  * **🔑 API Management**: Centralized control of your API keys and access credentials
  * **📊 Usage & Spending Tracking**: Monitor your API consumption and costs in real-time
  * **📱 Demo Apps Library**: Explore pre-built applications showcasing what's possible with Bigdata APIs
</Card>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.