# Create Tavily Search Feed

## User Intent

"How do I continuously search the web with Tavily? Show me web search feed configuration."

**Note**: Tavily API key is not required. Graphlit provides Tavily access by default and bills you for usage.

## Operation

**SDK Method**: `createFeed()` with FeedTypes.Search\
**Auth**: None required (Graphlit provides Tavily access, bills you for usage)

***

## Code Example (TypeScript)

```typescript
import { Graphlit } from 'graphlit-client';
import { FeedTypes, SearchServiceTypes } from 'graphlit-client/dist/generated/graphql-types';

const graphlit = new Graphlit();

const feed = await graphlit.createFeed({
  name: 'AI News Search',
  type: FeedTypes.Search,
  search: {
    type: SearchServiceTypes.Tavily,
    text: 'artificial intelligence news',
    readLimit: 20,
  },
  // Optional: add workflow for content processing
  // workflow: { id: workflow.createWorkflow.id }
});

console.log(`Created Tavily search feed: ${feed.createFeed.id}`);
```

***

## Configuration

**text**: Search query text\
**readLimit**: Number of results per execution\
**type**: `SearchServiceTypes.Tavily`

***

## What Gets Indexed

* Web page titles and URLs
* Page summaries and content
* Publication dates
* Relevance scores

***

## Use Cases

**News Monitoring**:

```typescript
text: 'artificial intelligence regulation policy'
```

**Research Topics**:

```typescript
text: 'quantum computing breakthroughs 2024'
```

**Company Mentions**:

```typescript
text: 'YourCompany product reviews'
```

**Technical Documentation**:

```typescript
text: 'GraphQL best practices tutorials'
```

***

## Search Service Alternatives

* **Tavily** - General web search (this guide)
* **Exa** - Semantic web search with embeddings
* **Podscan** - Podcast episode search

***

## Related

* [Exa Search Feed](/api-guides/use-cases/feeds/web/feed-create-exa-search.md) - Semantic web search
* [Podscan Feed](/api-guides/use-cases/feeds/web/feed-create-podscan-search.md) - Podcast search
* [RSS Feed](/api-guides/use-cases/feeds/web/feed-create-rss.md) - RSS/Atom feeds
* [Web Crawl](/api-guides/use-cases/feeds/web/feed-create-web-crawl.md) - Crawl specific sites


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.graphlit.dev/api-guides/use-cases/feeds/web/feed-create-tavily-search.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.