Document conversion is the act of converting one document's format to another, which allows the document to be read in many more applications. Documents can be converted into other source document formats, consumer formats or structured data.
Questions tagged [document-conversion]
70 questions
0
votes
1 answer
IBM Watson Document Conversion not working
I recently implemented the Document Conversion API from IBM Watson. I always get an encoding error for converting pdf document!!!
#!/usr/bin/env python
#coding: utf-8
import json
from watson_developer_cloud import DocumentConversionV1
from io…
Ikmel
- 11
- 1
- 4
0
votes
1 answer
Document Converstion for PDF form (eg. w2/1040/etc) as key/values instead of a single string based on font information
Trying to use the Document Conversion service to capture the json key/value pairs for the pdf documents such as (w2/1040/etc forms.)
Content of such forms in json response are coming as part of the "text" under the "content". Missing the form data,…
0
votes
1 answer
What is the rate limit for IBM's Document Conversion Service and how do I increase it?
We use IBM's Document Conversion service as a core part of our Watson-based AI system. Recently I have been getting a lot of this error whilst building our corpus:
Error SLM-THROTTLE occurred when accessing
…
David Powell
- 537
- 1
- 4
- 16
0
votes
0 answers
Receiving a "String index out of range: 0" when trying to convert a PDF in the IBM Document Conversion service
I am trying to convert a document using IBM's Document Conversion service. It is a basic PDF, 116 pages,1.1MB file. Nothing special about it that I can see, but the DC service returns the error "String index out of range: 0" when I try to convert…
David Powell
- 537
- 1
- 4
- 16
0
votes
1 answer
Why do I get "Could not push back" error when trying to use the IBM Bluemix Document Conversion service?
I am trying to convert documents using the Bluemix Document Conversion service with a Node.js application. I am getting nothing but errors in my app, but the test document I'm using converts fine using the demo page. Below is a minimal app that…
David Powell
- 537
- 1
- 4
- 16
0
votes
1 answer
Partial response of documentconversionV1()
I am trying to use DocumentConversionV1 function of watson_developer_cloud API on python , However the response in my case comes only as "<"Response 200">".
import sys
import os as o
import json
import codecs
from watson_developer_cloud import…
Sanjay Josh
- 87
- 6
0
votes
2 answers
How to use webfiles in document conversion of watson
We recently implemented the Document Conversion API from IBM Watson.In this can I use web files (www.something.com) as input.
curl -X POST -u "username":"password" -F config="{\"conversion_target\":\"answer_units\"}" -F…
user94
- 409
- 1
- 6
- 20
0
votes
1 answer
How to break up large document into smaller answer units on Retrieve and Rank?
I am still very new to Retrieve and Rank, and Document Conversion services, so I have been playing around with that lately.
I encountered a problem where when I upload a large document (100+ pages) - Retrieve and Rank would help me automatically…
Ngoodles
- 1
0
votes
0 answers
IBM Watson Document Conversion not working at all
We recently implemented the Document Conversion API from IBM Watson.
We always get the error, even though we specify the document type:
415 Unsupported Media Type - The media type of the input file is not supported. Specify the MIME type of the…
OSX55
- 160
- 2
- 10
0
votes
1 answer
Getting a strange error from Watson's Document Conversion service
I am trying to convert some documents into answer units with Watson's Document Conversion service, using the watson-developer-cloud Javascript library in Node.js. Certain ones (an example is at IBM internal link and is a .DOCX file) return this…
David Powell
- 537
- 1
- 4
- 16
0
votes
1 answer
Having trouble getting usable results from Watson's Document Conversion service
When I try to convert this document
https://public.dhe.ibm.com/common/ssi/ecm/po/en/poq12347usen/POQ12347USEN.PDF
with Watson's Document Conversion service, all I get is four answer units, one for each level-4 heading. What I really need is 47…
David Powell
- 537
- 1
- 4
- 16
0
votes
1 answer
Does IBM Watson Document Conversion ignores header?
We are trying to use the IBM Watson Document Conversion service on Word documents and have noticed that text that is in the header (and is displayed when the doc file is viewed) is not returned by the document conversion service. Is this a known…
Christopher Hyland
- 21
- 2
0
votes
1 answer
How to Handle Document Conversion from DocX and Other FileFormats to a Specific XSD?
We are trying to convert a .docx – and later other potential file formats – into a kind of standard XML. This XML is going to be mapped through an XSLT to the XML of our choice (xsd).
For the conversion to be successful, we need to keep as many of…
sbadea
- 1
- 2
0
votes
2 answers
While using document conversion with html in node-red, getting Error: Lost connection to server
Trying to use Watson Document Conversion service from Node-Red with following payload setup and to feed into 'Convert' node, it always returns "Error: Lost connect to server". I'd think the setup is right per the document, but hardly find a way to…
nyker
- 57
- 4
0
votes
1 answer
Bluemix PDF Document Conversion
I'm trying to convert a PDF document but I am having problems regarding the accents in words. The PDF is in Portuguese-Brazil language.
This is the command i'm running:
curl -X POST -u "OMITTED":"OMITTED" -F
…
Fred Miranda
- 31
- 4