documentloaders: implement simple client for apache tika

[ricardomaraschini]

Implements a very simple client to use Apache Tika for document parsing. An example usage has been added:

import (
        "context"
        "net/http"

        "github.com/tmc/langchaingo/documentloaders"
        "github.com/tmc/langchaingo/textsplitter"
)

// To run this example you need to run a Tika server and then set the address
// on the TikaURL constant. The easiest way of running a Tika server is by
// using Docker:
//
// $ docker run -d -p 9998:9998 apache/tika
//
// Tika will be listening on http://localhost:9998, you then just need to ajust
// the TikaURL constant.

const TikaURL = "http://localhost:9998"

func main() {
        resp, err := http.Get("https://www.golang-book.com/public/pdf/gobook.pdf")
        if err != nil {
                panic(err)
        }
        defer resp.Body.Close()

        splitter := textsplitter.NewRecursiveCharacter()
        tika := documentloaders.NewTika(TikaURL, resp.Body)
        docs, err := tika.LoadAndSplit(context.Background(), splitter)
        if err != nil {
                panic(err)
        }

        _ = docs
}

Feel free to just close this PR if this isn't necessary here. I am using it so I decided to contribute it back, no harm done.

PR Checklist

• Read the Contributing documentation.
• Read the Code of conduct documentation.
• Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• Describes the source of new concepts.
• References existing implementations as appropriate.
• Contains test coverage for new functions.
• Passes all golangci-lint checks.

[ricardomaraschini]

Yeah, lint is complaining. I will get back to this only if there is interest on this code.

[ricardomaraschini]

Yeah, lint is complaining. I will get back to this only if there is interest on this code.

Oh well, once in hell I may as well give Satan a hug. That was an easy fix.