Skip to content

change docling commands to convert to json instead of markdown #238

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

change docling commands to convert to json instead of markdown #238

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion beta/serverless-fleets/tutorials/docling/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

![](../../images/docling-picture.png)

This tutorial provides a comprehensive guide on using Docling to convert PDFs into Markdown format using serverless fleets. It leverages cloud object storage for managing both the input PDFs and the resulting Markdown files. The process is streamlined using IBM’s Code Engine to build the Docling container, which is then pushed to a container registry. Users can run a serverless fleet, which autonomously spawns workers to run the Docling container for efficient, scalable conversion tasks.
[Docling](https://docling-project.github.io/docling/) simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem. This tutorial provides a comprehensive guide on using Docling to convert PDFs into Markdown format using serverless fleets. It leverages [IBM Cloud Object Storage](https://www.ibm.com/de-de/products/cloud-object-storage) for managing the input (PDFs) and the output (Markdown) files. Users can run a serverless fleet, which autonomously spawns workers to run the Docling container for efficient, scalable conversion tasks. This tutorial uses the CPU version of the [docling container image](https://github.com/docling-project/docling-serve?tab=readme-ov-file#container-images) which can easily being replaced using the GPU version in combination with a Serverless GPU.

Key steps covered in the Tutorial:
1. Upload the examples PDFs to COS
Expand Down
22 changes: 11 additions & 11 deletions beta/serverless-fleets/tutorials/docling/commands.jsonl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/2203.01017v2.pdf", "--output", "/output/docling_2203.01017v2.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/2206.01062.pdf", "--output", "/output/docling_2206.01062.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/2305.03393v1-pg9.pdf", "--output", "/output/docling_2305.03393v1-pg9.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/2305.03393v1.pdf", "--output", "/output/docling_2305.03393v1.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/amt_handbook_sample.pdf", "--output", "/output/docling_amt_handbook_sample.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/code_and_formula.pdf", "--output", "/output/docling_code_and_formula.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/picture_classification.pdf", "--output", "/output/docling_picture_classification.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/redp5110_sampled.pdf", "--output", "/output/docling_redp5110_sampled.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/right_to_left_01.pdf", "--output", "/output/docling_right_to_left_01.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/right_to_left_02.pdf", "--output", "/output/docling_right_to_left_02.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "/input/pdfs/right_to_left_03.pdf", "--output", "/output/docling_right_to_left_03.pdf.md" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/2203.01017v2.pdf", "--output", "/output/docling_2203.01017v2.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/2206.01062.pdf", "--output", "/output/docling_2206.01062.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/2305.03393v1-pg9.pdf", "--output", "/output/docling_2305.03393v1-pg9.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/2305.03393v1.pdf", "--output", "/output/docling_2305.03393v1.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/amt_handbook_sample.pdf", "--output", "/output/docling_amt_handbook_sample.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/code_and_formula.pdf", "--output", "/output/docling_code_and_formula.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/picture_classification.pdf", "--output", "/output/docling_picture_classification.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/redp5110_sampled.pdf", "--output", "/output/docling_redp5110_sampled.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/right_to_left_01.pdf", "--output", "/output/docling_right_to_left_01.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/right_to_left_02.pdf", "--output", "/output/docling_right_to_left_02.pdf.json" ]}
{ "cmds":["docling"], "args": ["--num-threads", "12", "--to", "json", "/input/pdfs/right_to_left_03.pdf", "--output", "/output/docling_right_to_left_03.pdf.json" ]}
1 change: 0 additions & 1 deletion beta/serverless-fleets/tutorials/inferencing/run
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,6 @@ ibmcloud code-engine beta fleet create --name "fleet-${uuid}-1" \
--max-scale 1 \
--tasks-from-local-file commands.jsonl \
--gpu l40s:1 \
--cpu 24 \
--memory 120G \
--tasks-state-store fleet-task-store \
--mount-data-store /input=fleet-input-store:/inferencing \
Expand Down