ParallelExtractTool

Setup:

Install langchain-parallel and set environment variable PARALLEL_API_KEY.

pip install -U langchain-parallel
export PARALLEL_API_KEY="your-api-key"

Key init args:

api_key: Optional[SecretStr] Parallel API key. If not provided, will be read from PARALLEL_API_KEY env var. base_url: str Base URL for Parallel API. Defaults to "https://api.parallel.ai". max_chars_per_extract: Optional[int] Maximum characters per extracted result.

Instantiation:

from langchain_parallel import ParallelExtractTool

# Basic instantiation
tool = ParallelExtractTool()

# With custom API key and parameters
tool = ParallelExtractTool(
    api_key="your-api-key",
    max_chars_per_extract=5000
)

Invocation:

# Extract content from URLs
result = tool.invoke({
    "urls": [
        "https://example.com/article1",
        "https://example.com/article2"
    ]
})

# Result is a list of dicts with url, title, and content
for item in result:
    print(f"Title: {item['title']}")
    print(f"URL: {item['url']}")
    print(f"Content: {item['content'][:200]}...")

Response Format:

Returns a list of dictionaries, each containing:

• url: The URL that was extracted
• title: Title of the webpage
• content: Full extracted content as markdown
• publish_date: Publish date if available (optional)