GenAIScript

Scripting environment with convenient tooling for file ingestion, prompt development and structured data extraction.

• 👀 Read the documentation at https://microsoft.github.io/genaiscript/

Features

• 💵 Prompt programmatically using stylized JavaScript.

// define the context
def("FILE", env.files, { endsWith: ".pdf" })
// define the data
const schema = defSchema("DATA", { type: "array", items: { type: "string" } })
// define the task
$`Analyze FILE and
  extract titles to JSON compliant with ${schema}.`

• ⚡️ Edit, debug, run your scripts

• 📁 Scripts are files! They can be versioned, shared, forked, ...

• 📊 Define, validate, repair data using schemas. Zod support builtin.

const data = defSchema("MY_DATA",
    { type: "array", items: { ... }, })
$`Extract data from files using ${data} schema.`

• 📄 Ingest PDFs, DOCX, CSV, ... PDFs, DOCX, CSV, ...

const { pages } = await parsers.PDF(env.files[0])

• 🔍 Vector search

// embedding vector index and search
const files = await retrieval.vectorSearch("cats", env.files)

• 🚀 Automate using the CLI.

npx --yes genaiscript run my-script "*.pdf"

• 👯 compose prompts within prompts

// summarize each files individually
for (const file of env.files) {
    const { text } = await runPrompt((_) => {
        _.def("FILE", file)
        _.$`Summarize the FILE.`
    })
    // use result in main prompt
    _.def("SUMMARY", text)
}
// use summary
$`Summarize all the summaries.`

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.