Skip to content

UN-3987 [FIX] Send LLMWhisperer V2 params under the correct names #2236

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

Open
chandrasekharan-zipstack wants to merge 3 commits into
base: main
Choose a base branch
from
Open

UN-3987 [FIX] Send LLMWhisperer V2 params under the correct names #2236

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b1bda54
fix: send LLMWhisperer V2 params under the correct names
chandrasekharan-zipstack Aug 11, 2026
8b74d6f
feat: send the file name being extracted to LLMWhisperer
chandrasekharan-zipstack Aug 11, 2026
c4cde21
Commit uv.lock changes
chandrasekharan-zipstack Aug 12, 2026
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
2,018 changes: 1,009 additions & 1,009 deletions backend/uv.lock
View file
Open in desktop

Large diffs are not rendered by default.

1,554 changes: 777 additions & 777 deletions platform-service/uv.lock
View file
Open in desktop

Large diffs are not rendered by default.

1,232 changes: 616 additions & 616 deletions unstract/filesystem/uv.lock
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion unstract/sdk1/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ dependencies = [
"pdfplumber>=0.11.2",
"redis>=5.2.1",
# # LLMWhisperer client
"llmwhisperer-client>=2.6.2",
"llmwhisperer-client>=2.8.0",

@greptile-apps greptile-apps Bot Aug 12, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 SDK lock retains incompatible client

When unstract/sdk1 is installed from its own lockfile, the lock still resolves llmwhisperer-client 2.6.2 despite this new >=2.8.0 requirement. Frozen installation therefore rejects the stale lock, while workflows that install from it without synchronization retain a client that does not support the newly forwarded line_splitter_strategy, page_separator, and file_name arguments, causing V2 extraction calls to fail.

Knowledge Base Used: Unstract SDK, Core, and Flags

Prompt To Fix With AI 
This is a comment left during a code review.
Path: unstract/sdk1/pyproject.toml
Line: 50

Comment:
**SDK lock retains incompatible client**

When `unstract/sdk1` is installed from its own lockfile, the lock still resolves `llmwhisperer-client` 2.6.2 despite this new `>=2.8.0` requirement. Frozen installation therefore rejects the stale lock, while workflows that install from it without synchronization retain a client that does not support the newly forwarded `line_splitter_strategy`, `page_separator`, and `file_name` arguments, causing V2 extraction calls to fail.

**Knowledge Base Used:** [Unstract SDK, Core, and Flags](https://app.greptile.com/zipstack/-/custom-context/knowledge-base/zipstack/unstract/-/docs/unstract-sdk-core.md)

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.

Fix in Claude Code

# # Core utilities (Redis Sentinel-aware client factory, etc.)
"unstract-core",
]
Expand Down
5 changes: 4 additions & 1 deletion unstract/sdk1/src/unstract/sdk1/adapters/x2text/llm_whisperer_v2/src/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,12 +60,14 @@ class WhispererConfig:
MEDIAN_FILTER_SIZE = "median_filter_size"
GAUSSIAN_BLUR_RADIUS = "gaussian_blur_radius"
LINE_SPLITTER_TOLERANCE = "line_splitter_tolerance"
LINE_SPLITTER_STRATEGY = "line_spitter_strategy"
LINE_SPLITTER_STRATEGY = "line_splitter_strategy"
HORIZONTAL_STRETCH_FACTOR = "horizontal_stretch_factor"
PAGES_TO_EXTRACT = "pages_to_extract"
MARK_VERTICAL_LINES = "mark_vertical_lines"
MARK_HORIZONTAL_LINES = "mark_horizontal_lines"
# Misspelling retained: correcting the JSON schema key means migrating saved configs
PAGE_SEPARATOR = "page_seperator"
PAGE_SEPARATOR_PARAM = "page_separator"
URL_IN_POST = "url_in_post"
TAG = "tag"
USE_WEBHOOK = "use_webhook"
Expand All @@ -78,6 +80,7 @@ class WhispererConfig:
INCLUDE_LINE_CONFIDENCE = "include_line_confidence"
EXTRACT_ALL_LINES = "extract_all_lines"
LINES = "lines"
FILE_NAME = "file_name"


class WhisperStatus:
Expand Down
4 changes: 3 additions & 1 deletion unstract/sdk1/src/unstract/sdk1/adapters/x2text/llm_whisperer_v2/src/helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,7 +200,7 @@ def get_whisperer_params(
WhispererConfig.MARK_HORIZONTAL_LINES,
WhispererDefaults.MARK_HORIZONTAL_LINES,
),
WhispererConfig.PAGE_SEPARATOR: config.get(
WhispererConfig.PAGE_SEPARATOR_PARAM: config.get(
WhispererConfig.PAGE_SEPARATOR,
WhispererDefaults.PAGE_SEPARATOR,
),
Expand Down Expand Up @@ -260,6 +260,8 @@ def send_whisper_request(
params = LLMWhispererHelper.get_whisperer_params(
config=config, extra_params=extra_params
)
# Recorded against the extraction for cross referencing in usage reports
params[WhispererConfig.FILE_NAME] = Path(input_file_path).name
response: requests.Response
try:
input_file_data = BytesIO(fs.read(path=input_file_path, mode="rb"))
Expand Down
27 changes: 27 additions & 0 deletions unstract/sdk1/tests/test_llm_whisperer_v2_params.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
"""Tests for the query params the LLMWhisperer V2 adapter sends."""

from unstract.sdk1.adapters.x2text.llm_whisperer_v2.src.dto import (
WhispererRequestParams,
)
from unstract.sdk1.adapters.x2text.llm_whisperer_v2.src.helper import LLMWhispererHelper


def _params(config: dict) -> dict:
return LLMWhispererHelper.get_whisperer_params(
config=config, extra_params=WhispererRequestParams()
)


def test_line_splitter_strategy_from_config() -> None:
"""The key stored by the adapter's JSON schema is the one that is read."""
params = _params({"line_splitter_strategy": "right-priority"})

assert params["line_splitter_strategy"] == "right-priority"


def test_page_separator_read_under_legacy_config_key() -> None:
"""Existing configs store the misspelled key but the client kwarg is correct."""
params = _params({"page_seperator": "<<< {{page_no}} >>>"})

assert params["page_separator"] == "<<< {{page_no}} >>>"
assert "page_seperator" not in params
12 changes: 6 additions & 6 deletions workers/uv.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.