Wiro - Rag Chat Github icon

Wiro - Rag Chat Github

Instantly retrieve and analyze content from any GitHub repository. Select your LLM model, extra

Wiro - Rag Chat Github

AI-generated

Overview

This node integrates with the Wiro API to retrieve and analyze content from any GitHub repository using a selected large language model (LLM). It allows users to specify GitHub repository details, authentication tokens, and various model parameters to generate responses based on prompts. Common use cases include querying codebases, documentation, or other repository content for insights, summaries, or code-related assistance.

Use Case Examples

  1. A developer wants to query a public GitHub repository to get explanations or summaries of the code.
  2. A team uses the node to analyze private repositories by providing a GitHub access token, enabling secure content retrieval and interaction.
  3. Users customize model parameters like temperature and token limits to tailor the response style and length for different tasks such as code generation or documentation review.

Properties

Name Meaning
Select Model The large language model to use for processing the prompt.
Select Model Private Private model selection option, possibly for private or custom models.
Github Repo Owner Name The owner of the GitHub repository to retrieve content from.
Github Repo Name The name of the GitHub repository to retrieve content from.
Github Branch Name The branch of the GitHub repository to target.
Github Access Token GitHub access token for accessing private repositories; leave blank for public repositories.
Prompt The prompt text to send to the language model for generating a response.
User ID Unique identifier for the user to store and retrieve chat history specific to that user.
Session ID Identifier for a specific 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 Controls 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 the query.
Seed Seed value for randomization control in model output.
Quantization Enables quantization to reduce model precision for lower memory usage and faster inference.
Do Sample Controls whether the model generates text deterministically or with randomness.

Output

JSON

  • taskid - Unique identifier for the processing task.
  • message - The generated response or message from the model.
  • status - Status of the task, e.g., 'completed' or 'failed'.

Dependencies

  • Wiro API with API key and secret for authentication

Troubleshooting

  • If the node throws an error about missing task ID or socket access token, verify that the Wiro API credentials are correct and the API is reachable.
  • Ensure the GitHub access token is valid and has appropriate permissions for private repositories.
  • If the response is empty or incomplete, check model parameters like maxNewOutputLength and contextWindow to ensure they are set appropriately.

Links

  • Wiro API Endpoint - API endpoint used by the node to run the Rag Chat Github operation.

Discussion