# ❜embed - The AI Recommendation System for Web3 Documentation

## Guides
- [Algorithm Engine for Web3 Builders](https://docs.getembed.ai/docs/algorithm-engine-for-web3-builders.md)
- [Mission and Principles](https://docs.getembed.ai/docs/mission-and-principles.md)
- [Our Roadmap](https://docs.getembed.ai/docs/our-roadmap-1.md)
- [Compute units pricing](https://docs.getembed.ai/docs/compute-units-pricing.md): v2 Pricing from August 8th, 2025 - currently ongoing
- [Step 1: Candidate Generation](https://docs.getembed.ai/docs/candidate-generation.md)
- [Step 4: Feed Construction](https://docs.getembed.ai/docs/construction.md)
- [Data Sources](https://docs.getembed.ai/docs/data-sources.md)
- [Get personalized feed recommendations](https://docs.getembed.ai/docs/deployment.md)
- [The ❜embed AI pipeline](https://docs.getembed.ai/docs/embed-pipeline-improved-draft.md)
- [Feed deployment status](https://docs.getembed.ai/docs/feed-deployment-status.md)
- [Step 2: Ranking](https://docs.getembed.ai/docs/re-ranking.md)
- [Step 3: Visibility Filters](https://docs.getembed.ai/docs/step-3-visibility-filters.md)
- [Glossary](https://docs.getembed.ai/docs/glossary.md)
- [Essentials - What Makes a Good Feed?](https://docs.getembed.ai/docs/essentials-what-makes-a-good-feed.md): Let's take a brief look at the main characteristics at a good feed, from personalization to spam.
- [Feed Builder & feed_id 101](https://docs.getembed.ai/docs/feed-builder-101.md): A quick introduction to our no-code feed builder and feed objects.
- [Feed Builder & feed_id 201](https://docs.getembed.ai/docs/feed-builder-201.md): The full walkthrough of the Feed Builder's killer features and how to use them.
- [Authentication](https://docs.getembed.ai/docs/authentication.md)
- [❜embed SDK quickstart](https://docs.getembed.ai/docs/embed-sdk-quickstart.md)
- [Getting Started - Your First Feed](https://docs.getembed.ai/docs/getting-started-your-first-feed-1.md)
- [@embed-ai/sdk ](https://docs.getembed.ai/docs/embed-aisdk.md)
- [Render a Feed in a Farcaster App using React](https://docs.getembed.ai/docs/content-discovery-api-for-rag-summaries-and-insights.md)
- [Develop a Zora Feed App with NextJS and Base MiniKit](https://docs.getembed.ai/docs/develop-a-zora-feed-app-with-nextjs-and-base-minikit.md): A few steps to create a personalized Zora feed where users can buy social media posts.
- [Develop AI Agents that leverage recommendations](https://docs.getembed.ai/docs/develop-ai-agents-that-leverage-recommendations.md)

## API Reference
- [Data Ingestion](https://docs.getembed.ai/reference/data-ingestion.md)
- [Ingest item data](https://docs.getembed.ai/reference/ingestitems.md): Ingest content items (posts, articles, videos, etc.) from various protocols
- [Ingest user data](https://docs.getembed.ai/reference/ingestusers.md): Ingest user profile data from various protocols
- [Track item interactions](https://docs.getembed.ai/reference/trackiteminteractions.md): Track user interactions with content items
- [Track user interactions](https://docs.getembed.ai/reference/trackuserinteractions.md): Track user interactions (uses same schema as item interactions but routes to different stream)
- [Get personalized Polymarket recommendations](https://docs.getembed.ai/reference/get_pm_recommendations-1.md): Generate personalized Polymarket market recommendations for a wallet address.  This endpoint uses a two-stage recommendation architecture:  1. **Candidate Generation**: Filters, boosts, and sorts markets to generate candidate recommendations  2. **Reranking**: Personalizes and reorders candidates based on user behavior  **Candidate Filtering:**  Use `filters.candidate_filters` for advanced filtering and relevance boosting.  **Filter Types:**  - `term`: Exact match for single value (e.g., `{"filter": "term", "field": "active", "value": true}`)  - `terms`: Match any of multiple values (e.g., `{"filter": "terms", "field": "ai_labels_high", "value": ["mbd2:t_sports"]}`)  - `numeric`: Numeric comparison (e.g., `{"filter": "numeric", "field": "volume_1yr", "value": 100, "operator": ">="}`)  - `date`: Date range filter (e.g., `{"filter": "date", "field": "end_date", "value": {"date_from": "", "date_to": "2026-01-01"}}`)  - `match`: Text search (e.g., `{"filter": "match", "field": "question", "value": ["bitcoin"]}`)  **Scoring Methods:**  - `none`: No reranking, returns candidates in original order  - `hrnn_v0`: Personalized reranking based on user trading history and behavior
- [Manage feed status](https://docs.getembed.ai/reference/get-recommendations.md)
- [Get personalized feed recommendations](https://docs.getembed.ai/reference/getforyoufeed-1.md): ## Overview  The recommendations endpoint delivers personalized content feeds tailored to individual users. This endpoint consumes feed configurations (referenced via `feed_id`) to generate ranked lists of content from Farcaster posts or Zora posts.  ## Key Concepts  - **Feed Configuration**: Pre-configured feeds created via the Feed Management API define filtering, scoring, and ranking logic - **Personalization**: Recommendations are customized per user based on their interaction history, following graph, and preferences - **Feed Sources**: Supports both Farcaster items (posts) and Zora coins (posts) - **Override Parameters**: Any parameters passed directly to the API override those saved in the `feed_id` configuration  ## Usage  Returns a list of recommended items (posts or Zora posts) for a specific user - items the user is most likely to interact with. The `feed_id` parameter lets you use preconfigured filters and ranking logic from the console, while direct API parameters provide runtime overrides.
- [Create a feed configuration](https://docs.getembed.ai/reference/createfeedconfig.md): ## Overview  The Feed Management API enables you to create, configure, and manage personalized content feeds. Define how content is sourced, filtered, ranked, and presented to users.  ## Key Concepts  - **Feed Configuration**: Define the complete behavior of a feed including candidate sources, filters, scoring algorithms, and diversity controls - **Candidate Sources**: Choose between Farcaster items (casts) or Zora coins (posts) as content sources - **Filtering**: Apply sophisticated filters including AI labels, engagement metrics, publication types, keywords, and more - **Scoring & Ranking**: Select from various algorithms (trending, popular, user affinity, interest-based) or build custom weighted scoring - **Feed ID**: Each configuration generates a unique `feed_id` that can be used in the recommendations endpoint  ## Usage  Create and manage feed configurations that control how content is generated, filtered, and ranked. You can generate candidates from Farcaster or Zora, apply filters to include/exclude specific content, rank items using various algorithms, and mix multiple feeds together. The output is a `feed_id` that can be used when calling the recommendations endpoint.
- [Delete a feed configuration](https://docs.getembed.ai/reference/deletefeedconfig.md): Permanently delete a feed configuration by its `feed_id`. This action cannot be undone. Once deleted, the feed will no longer be available for use in recommendations. Ensure you have the appropriate permissions (delete scope) on your API key to perform this operation.
- [Retrieve a feed configuration](https://docs.getembed.ai/reference/getfeedconfig.md): Retrieve a specific feed configuration by its `feed_id`. Returns the complete feed configuration including filters, scoring settings, diversity controls, and all other configured parameters. Use this endpoint to inspect or copy existing feed configurations.
- [Retrieve saved feed config list](https://docs.getembed.ai/reference/listfeedconfigs.md): Retrieve a list of all feed configurations accessible to your API key. Use the `visibility` parameter to filter by private or public feeds. Returns an array of feed configurations including their IDs, names, status, and full configuration details.
- [Ban specific casts by item ID](https://docs.getembed.ai/reference/banitems.md): ## Overview  The Moderation API provides organization-wide content and user management controls. Maintain lists of banned items and users that apply across all your feed configurations.  ## Key Concepts  - **Organization-Wide**: Banned items and users apply to all feeds within your organization - **Item Bans**: Block specific casts by their item ID (hash) from appearing in any feed - **User Bans**: Block all content from specific users (by FID) across all feeds - **Persistent Lists**: Ban lists persist until explicitly removed, providing ongoing content control  ## Usage  Manage the lists of banned casts and banned users across your organization. These endpoints let you add items/users to the ban list, remove them, or retrieve the current list of banned items and users. All moderation endpoints require your API keys for authentication.
- [Ban specific users by user ID](https://docs.getembed.ai/reference/banusers.md): Add users to the organization-wide ban list by providing their FIDs (Farcaster IDs). Once banned, all content from these users will be excluded from all feed configurations in your organization. The ban list persists until explicitly removed.
- [Retrieve the current banned items list](https://docs.getembed.ai/reference/listbanneditems.md): Retrieve the complete list of all currently banned cast item IDs (hashes) for your organization. This list applies to all feed configurations and prevents these items from appearing in any feed until they are removed from the ban list.
- [Retrieve the current banned users list](https://docs.getembed.ai/reference/listbannedusers.md): Retrieve the complete list of all currently banned user IDs (FIDs) for your organization. This list applies to all feed configurations and prevents all content from these users from appearing in any feed until they are removed from the ban list.
- [Remove specific casts from the ban list](https://docs.getembed.ai/reference/unbanitems.md): Remove specific casts from the organization-wide ban list by providing their item IDs (hashes). Once removed, these items will be eligible to appear in feeds again. The ban list applies across all feed configurations in your organization.
- [Remove specific users from the ban list](https://docs.getembed.ai/reference/unbanusers.md): Remove specific users from the organization-wide ban list by providing their FIDs (Farcaster IDs). Once removed, content from these users will be eligible to appear in feeds again. The ban list applies across all feed configurations in your organization.