docs: add broker reports batch processing example - #3976
Open
PAUL01zjb wants to merge 3 commits into
Open
Conversation
Add a convert -> export -> audit example that batch-processes Chinese PDF broker reports to Markdown with referenced figures, and list it in the examples index. Signed-off-by: PAUL01zjb <PAUL01zjb@users.noreply.github.com>
Contributor
|
✅ DCO Check Passed Thanks @PAUL01zjb, all your commits are properly signed off. 🎉 |
Contributor
Merge Protections🟢 Merge protection satisfied — ready to merge. Show 1 satisfied protection🟢 Enforce conventional commitMake sure that we follow https://www.conventionalcommits.org/en/v1.0.0/
|
dolfim-ibm
requested changes
Aug 11, 2026
dolfim-ibm
left a comment
Member
There was a problem hiding this comment.
@PAUL01zjb your example looks like a simple convert + metadata report. I don't see anything specific about broker reports (no such example data, no specific output analysis.
My suggestion is
- We could keep a simple generic example. Then rephrase it as (for example) convert and metadata report.
- Or you could make the example much more specific, e.g. use some real data, do some specific information extraction, some visualization of the data in the report, etc
Add a bundled sample broker report (synthetic, Chinese) and extend the example to extract key financial metrics from report tables into JSON, render an optional revenue/net-profit chart, and audit per-file results. Signed-off-by: PAUL01zjb <PAUL01zjb@users.noreply.github.com>
Signed-off-by: PAUL01zjb <PAUL01zjb@users.noreply.github.com>
Author
|
Thanks for the review! I have updated the example to be genuinely
broker-specific:
- Bundled sample data: docs/examples/data/broker_report_sample.pdf, a
synthetic Chinese broker report (key-financials table + NIM trend figure),
so the example runs out of the box.
- Specific information extraction: the script now walks the detected tables
and extracts key financial metrics (revenue, net profit, net profit growth,
ROE, NPL ratio, provision coverage, EPS, PE, PB) into a compact JSON
summary aligned to report periods (2024A / 2025E / 2026E).
- Output analysis: a per-file audit (pages / tables / pictures / extracted
metrics) plus an optional revenue-vs-net-profit chart rendered with
matplotlib when available (graceful fallback otherwise).
The pipeline is still convert -> export -> audit, but the audit is now a
machine-readable metrics summary rather than a bare metadata report.
Michele Dolfi ***@***.***> 于2026年8月11日周二 15:39写道:
… ***@***.**** requested changes on this pull request.
@PAUL01zjb <https://github.com/PAUL01zjb> your example looks like a
simple convert + metadata report. I don't see anything specific about
broker reports (no such example data, no specific output analysis.
My suggestion is
1. We could keep a simple generic example. Then rephrase it as (for
example) convert and metadata report.
2. Or you could make the example much more specific, e.g. use some
real data, do some specific information extraction, some visualization of
the data in the report, etc
—
Reply to this email directly, view it on GitHub
<#3976?email_source=notifications&email_token=BMSYMAQ4UQSNL2XUUY2TUHL5JLEUPA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTIOJQGM4TKOJTG4Y2M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJLDGN5XXIZLSL5RWY2LDNM#pullrequestreview-4903959371>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/BMSYMAT4ZNHFSCHBTAYLI435JLEUPAVCNFSNUABFKJSXA33TNF2G64TZHM4DENRRGY4DCNRQHNEXG43VMU5TKMJRG43TAMZTGU32C5QC>
.
Triage notifications, keep track of coding agent tasks and review pull
requests on the go with GitHub Mobile for iOS
<https://github.com/notifications/mobile/ios/BMSYMAURGN5JBC3WHLOZPNT5JLEUPA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTIOJQGM4TKOJTG4Y2M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJKTGN5XXIZLSL5UW64Y>
and Android
<https://github.com/notifications/mobile/android/BMSYMAVMHA4CSCFSKA65TYL5JLEUPA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTIOJQGM4TKOJTG4Y2M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJLTGN5XXIZLSL5QW4ZDSN5UWI>.
Download it today!
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a convert -> export -> audit example that batch-processes Chinese PDF broker reports to Markdown with referenced figures, and list it in the examples index.
Checklist: