Skip to content

Extractor

The main entry point for tool output extraction.

ToolOutputExtractor(model_path=None, base_url=None, model_name=None, max_length=4096, device='auto')

Extract relevant lines from tool output using a fine-tuned model.

Supports three backends: - vLLM/OpenAI-compatible server: pass base_url - Local transformers (generative): pass model_path - Encoder (discriminative): auto-detected from model config, or backend="encoder"

Usage: # vLLM (connects to running server) extractor = ToolOutputExtractor(base_url="http://localhost:8000/v1")

# Local generative
extractor = ToolOutputExtractor(model_path="./output/qwen-lora")

# Encoder (auto-detected)
extractor = ToolOutputExtractor(model_path="./output/squeez_encoder")

filtered = extractor.extract(task="Fix the bug", tool_output=raw)

extract(task, tool_output, max_new_tokens=1024, temperature=0.1)

Extract relevant lines from tool output.

Args: task: Description of the coding task/issue tool_output: Raw tool output text max_new_tokens: Maximum tokens to generate temperature: Sampling temperature

Returns: Filtered output containing only relevant lines


Helper functions

_format_prompt(task, tool_output)

Format the input prompt using Qwen ChatML template.