Jina DeepSearch

Jina DeepSearch is an advanced AI-powered search and reasoning API that performs iterative web searches to find and synthesize information from multiple sources. The Jina DeepSearch connector enables you to interact with Jina's DeepSearch API for intelligent web search, iterative reasoning, and comprehensive information retrieval. This connector is particularly useful for applications that need to perform deep web searches, gather information from multiple sources, build research assistants, or create AI-powered search and discovery systems.

Power end-to-end data operations for your Jina DeepSearch API with Nexla. Our bi-directional Jina DeepSearch connector is purpose-built for Jina DeepSearch, making it simple to ingest data, sync it across systems, and deliver it anywhere — all with no coding required. Nexla turns API-sourced data into ready-to-use, reusable data products and makes it easy to send data to Jina DeepSearch or any other destination. With comprehensive monitoring, lineage tracking, and access controls, Nexla keeps your Jina DeepSearch workflows fast, secure, and fully governed.

Features

Type: API

SourceDestination

• Seamless API Integration: Connect to any endpoint as source or destination without coding, with automatic data product creation
• Visual Composition & Chaining: Build complex integrations using visual templates, chain API calls, and compose workflows with data validation and filtering
• API Proxy: Expose curated slices of your data securely with a secure and customizable API proxy that validates and transforms data on the fly
• Request optimization with intelligent batching, retry, and caching to minimize API calls and costs

Prerequisites

Before creating a Jina DeepSearch credential, you'll need to obtain an API key from your Jina AI account. Jina AI provides API keys for programmatic access to their DeepSearch service through the API dashboard.

To obtain a Jina AI API key:

1. Log in to your Jina AI account at https://jina.ai or create an account if you don't have one.

2. Navigate to the API dashboard at https://jina.ai/api-dashboard/ or access it from your Jina AI account settings.

3. In the API dashboard, locate the section for API key management. This is typically found in your account settings or a dedicated API/Developer section.

4. Click Create API Key or Generate New Key to create a new API key for your application.

5. Copy the API key immediately after generation, as it may only be displayed once for security purposes. Store it securely, as you'll need it to authenticate API requests.

For detailed information about Jina AI API authentication and API key management, refer to the Jina DeepSearch Documentation and Jina AI API Dashboard.

Authenticate

Credentials required

Field	Required	Secret	Description
API Key	Yes	Yes	Jina-provided secret API key
Base URL	Yes	No	The base URL for the Jina Deepsearch AI API.
API Version	Yes	No	Parameter for defining the API version for Jina Deepsearch API requests
Payload to test	Yes	No	Chat completions payload to test a connection

Create a credential in Nexla

1. After selecting the data source/destination type, click the Add Credential tile to open the Add New Credential overlay.

New Credential Overlay – Jina DeepSearch

2. Enter a name for the credential in the Credential Name field and a short, meaningful description in the Credential Description field.

3. In the API Key field, enter the API key that you obtained from your Jina AI API dashboard. This is the secret API key used to authenticate requests to the Jina DeepSearch API.

4. In the Base URL field, enter the base URL for the Jina DeepSearch API. The default value is https://deepsearch.jina.ai, which is the standard base URL for Jina DeepSearch API services. You can specify a different base URL if your organization uses a custom endpoint.

5. In the API Version field, enter the API version you want to use. The default value is v1, which is the current version of the Jina DeepSearch API. You can specify a different version if your organization uses a specific API version.

6. In the Payload to test field, enter a sample JSON payload to test the connection. A default payload is provided:

   {
     "model": "jina-deepsearch-v1",
     "messages": [
         {
             "role": "user",
             "content": "Hi!"
         },
         {
             "role": "assistant",
             "content": "Hi, how can I help you?"
         },
         {
             "role": "user",
             "content": "what's the latest blog post from jina ai?"
         }
     ],
     "reasoning_effort": "low",
     "budget_tokens": 10,
     "max_attempts": 1,
     "no_direct_answer": false,
     "only_hostnames": [
         "researchgate.net"
     ]
   }

7. Click the Save button at the bottom of the overlay. The newly added credential will now appear in a tile on the Authenticate screen during data source/destination creation.

Use as a data source

To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Select the Jina DeepSearch connector tile, then select the credential that will be used to connect to the Jina DeepSearch API, and click Next; or, create a new Jina DeepSearch credential for use in this flow.

Endpoint templates

Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Jina DeepSearch API endpoints. Select the endpoint from which this source will fetch data from the Endpoint pulldown menu. Available endpoint templates are listed in the expandable boxes below.

Chat Completions

This endpoint generates chat-based completions using Jina's DeepSearch API, which performs iterative web searches to find and synthesize information. Use this endpoint when you need to perform deep web searches, gather information from multiple sources, build research assistants, or create AI-powered search and discovery systems.

• Enter the model ID to use in the Model field. The default value is jina-deepsearch-v1, which is the current DeepSearch model. You can specify a different model if your organization uses a specific model version.
• Enter an array of message objects for the chat in the Messages field. Messages should be formatted as a JSON array, for example: [{"role": "user", "content": "Hello!"}]. Each message object should have a role field (typically "user" or "assistant") and a content field containing the message text.
• Optionally, specify whether to stream the response in the Stream field. The default value is false. Set to true if you want to receive streaming responses.
• Optionally, specify the level of reasoning effort in the Reasoning Effort field. Valid values are low, medium, or high. The default value is medium. Higher reasoning effort may provide more thorough search results but may take longer to process.
• Optionally, enter the maximum number of tokens allowed for the DeepSearch process in the Budget Tokens field. The default value is 100000. This controls the computational budget for the search and reasoning process.
• Optionally, enter the maximum number of retries for solving a problem in the Max Attempts field. The default value is 3. This controls how many times the API will attempt to find an answer before giving up.
• Optionally, specify whether to force the model to take further steps even for trivial queries in the No Direct Answer field. The default value is false. Set to true to force deeper search and reasoning.
• Optionally, enter the maximum number of URLs to include in the final answer in the Max Returned URLs field. The default value is 5. This controls how many source URLs are included in the response.
• Optionally, specify whether to enable structured outputs matching a supplied JSON schema in the Structured Output field. The default value is false.
• Optionally, enter a list of domains given higher priority for content retrieval in the Good Domains field. This should be formatted as a JSON array, for example: ["example.com", "researchgate.net"].
• Optionally, enter a list of domains to be excluded from content retrieval in the Bad Domains field. This should be formatted as a JSON array.
• Optionally, enter a list of domains to be exclusively included in content retrieval in the Only Domains field. This should be formatted as a JSON array.
• Optionally, specify the language of the answer in the Answer Language field. Use ISO 639-1 language codes (e.g., en for English, fr for French). The default value is en.

The Chat Completions endpoint uses POST requests to send chat messages to the Jina DeepSearch API, which then performs iterative web searches and reasoning to generate comprehensive answers. The endpoint returns chat completions with synthesized information from multiple web sources. For more information about the Chat Completions endpoint, refer to the Jina DeepSearch Documentation.

Once the selected endpoint template has been configured, click the Test button to the right of the endpoint selection menu to retrieve a sample of the data that will be fetched. Sample data will be displayed in the Endpoint Test Result panel on the right, allowing you to verify that the source is configured correctly before saving.

Manual configuration

Jina DeepSearch data sources can also be manually configured to ingest data from any valid Jina DeepSearch API endpoint, including endpoints not covered by the pre-built templates, chained API calls, or custom request parameters. Jina DeepSearch API endpoints typically follow the pattern {base_url}/{api_version}/chat/completions, where {base_url} is typically https://deepsearch.jina.ai and {api_version} is typically v1. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, endpoint URL, date/time and lookup macros, path to data, metadata, and request headers.

For Jina DeepSearch API responses, common paths to data include $.choices[*].message.content for chat completion content. You may want to include the Content-Type:application/json request header to specify the request format.

Once all of the relevant settings have been configured, click the Create button in the upper right corner of the screen to save and create the new Jina DeepSearch data source. Nexla will now begin ingesting data from the configured endpoint and will organize any data that it finds into one or more Nexsets.