langextract
langextract copied to clipboard
google
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
It would be good if the extraction output is based on a user-specified schema. The output has no structure now.
**Describe the overall issue and situation** When attempting to follow the batch tutorial at https://github.com/google/langextract/blob/main/docs/examples/batch_api_example.md, an error occurs when reading the batch predictions with: `Traceback (most recent call last): File...
### Describe the overall issue and situation When using version 1.1.1 to extracting Chinese text, `char_interval` is no longer empty, but it is not very accurate. ### Expected behavior An...
This PR adds an option to initialize a gemini model based on a Google Cloud platform project's SA key using the project name + location. This is helpful for situations...
# Description This PR adds conda installation instructions and associated status badge for documentation. Fixes #30 # How Has This Been Tested? This is a purely documentation change. The tests...
# Description Fixes #237 - GPT-5-mini reasoning_effort Parameter Issue ## Problem When using `reasoning_effort` parameter with GPT-5 models, the following error occurred: `Exception: OpenAI API error: Completions.create() got an unexpected...
fixes #256 This PR aligns the Ollama provider with the Ollama API by sending keep_alive at the payload’s top level while keeping options.keep_alive for backward compatibility. Changes Provider: compute keep_alive...
Due to regional settings of the operating system, if the tag does not specify the charset, the browser may default to a non-UTF-8 encoding, resulting in garbled text.
Hello, I’m Zhantao Wang, currently working/studying at Digital China. I have experience in AI. I am passionate about open-source projects and hope to contribute to the community through this PR....
