Intro:

The Weaviate Integration Actor from Apify allows users to transfer selected data from various Apify Actors into a Weaviate database. This integration is particularly useful for those looking to leverage vector databases for AI-driven applications, enhancing their data retrieval and processing capabilities.

🔍 What Is Weaviate Integration?

Weaviate Integration is an API that processes and transfers data into a Weaviate vector database, allowing for semantic search and machine learning applications. It extracts relevant data, computes text embeddings, and saves them in Weaviate, making it valuable for developers, data scientists, and businesses looking to enhance their data-driven decision-making processes.

✨ Features

• Data Transfer: Move data from Apify Actors to Weaviate seamlessly.

• Incremental Updates: Update only changed data to minimize unnecessary processing.

• Chunk Processing: Optionally split large datasets into manageable chunks.

• Customizable Fields: Specify which fields to save and how to utilize them as metadata.

• Embeddings Support: Use various providers like OpenAI and Cohere for computing embeddings.

• Flexible Update Strategies: Choose between adding, upserting, or using delta updates for data management.

🛠️ How to Use It

Step-by-step tutorial:

1. Go to the tool’s page: Weaviate Integration Tool

2. Click “Try for free” or “Run actor”.

3. Fill in the required input fields:

   • weaviateUrl: Your Weaviate database URL.

   • weaviateApiKey: Your API key for the Weaviate database.

   • weaviateCollectionName: The name of the collection in Weaviate.

   • [Optional] embedDataField: Specify which field contains the textual data for embedding.

4. Click “Run” and wait for results to be generated.

5. Download results or send to a webhook endpoint as required.

🧪 Sample Input (JSON)

json { "weaviateUrl": "https://apify-e2g4df23k.weaviate.network", "weaviateApiKey": "YOUR-WEAVIATE-API-KEY", "weaviateCollectionName": "YOUR-WEAVIATE-COLLECTION-NAME", "embeddingsApiKey": "YOUR-OPENAI-API-KEY", "embeddingsProvider": "OpenAI", "embeddingsConfig": { "model": "text-embedding-3-small" }, "datasetFields": ["text"], "dataUpdatesStrategy": "deltaUpdates", "dataUpdatePrimaryDatasetFields": ["url"] }

📤 Output Data (Fields)

• id: Unique identifier for the record.

• last_seen_at: Timestamp of the last time this data was processed.

• text: The processed text from the dataset.

• metadata: Additional metadata like titles or descriptions.

💰 Pricing This actor is priced at $0.0011/Operation. Apify offers a free tier for users to try out their tools and integrations.

👨‍💻 Built By Apify Team — from Apify.com

✅ Final Thoughts The Weaviate Integration Actor is a must-try for anyone looking to streamline their data management and enhance their AI applications. By allowing for efficient data transfers and updates, it's especially valuable for developers and researchers looking to leverage the power of vector databases.

🔗 Try the Actor Now 👉 Weaviate Integration Tool