Wiro - Rag Chat Website icon

Wiro - Rag Chat Website

Instantly retrieve and analyze content from any website URL. Select your LLM model, fetch key i

Wiro - Rag Chat Website

AI-generated

Overview

This node integrates with the Wiro API to retrieve and analyze content from any specified website URL using a selected language model. It allows users to send a prompt along with various parameters to customize the model's behavior and receive a processed response. Common scenarios include extracting insights from web content, generating summaries, or answering questions based on website data.

Use Case Examples

  1. A user inputs a website URL and a prompt asking for a summary of the page content. The node fetches the content, processes it with the selected model, and returns a concise summary.
  2. A user provides a URL and a question related to the website's content. The node uses the model to analyze the page and generate an answer based on the retrieved information.

Properties

Name Meaning
Select Model The language model to use for processing the website content.
Select Model Private An alternative private model option for processing.
Website URL The URL of the website to retrieve and analyze content from.
Prompt The prompt or query to send to the model for generating a response.
User ID A unique identifier for the user to store and retrieve chat history specific to that user.
Session ID A unique identifier for a session to manage multiple sessions for the same user.
System Prompt A system prompt prepended to the user prompt to guide the model's behavior.
Temperature Adjusts randomness of the model's output; 0 is deterministic, higher values increase randomness.
Top P Samples from the top p percentage of most likely tokens during text decoding.
Top K Samples from the top k most likely tokens during text decoding.
Chunk Size Size of each chunk of text processed during retrieval phase, affecting context and performance.
Chunk Overlap Number of tokens overlapping between chunks to ensure continuity.
Similarity Top K Number of most similar documents or chunks to retrieve based on similarity scores.
Context Window Maximum number of tokens the model can process at once, including input and retrieved chunks.
Max New Tokens Maximum number of tokens the model can generate in response to a query.
Seed Seed value for randomization control in model output.
Quantization Enables reduced precision of model weights to decrease memory usage and improve speed, with possible slight quality impact.
Do Sample Controls whether the model generates text deterministically or with randomness.

Output

JSON

  • taskid - Identifier of the processing task.
  • message - The response message generated by the model after processing.
  • status - Status of the task, indicating if it completed successfully or failed.

Dependencies

  • Wiro API with API key and secret for authentication

Troubleshooting

  • If the node throws an error indicating missing task ID or socket access token, it means the Wiro API response was invalid or incomplete. Check API credentials and request parameters.
  • If the task status is 'failed', the processing did not complete successfully. Review the prompt, URL, and model selection for correctness.
  • Network or authentication issues may prevent successful API calls; ensure valid API keys and network connectivity.

Links

Discussion