mirror of
https://github.com/run-llama/llama_cloud_services.git
synced 2026-07-21 03:55:22 -04:00
Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 986d3987d3 | |||
| 1bf522311f | |||
| 24166dcfc8 |
@@ -1,5 +1,12 @@
|
||||
# llama-cloud-services-py
|
||||
|
||||
## 0.6.74
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- 1bf5223: Fix default bbox values
|
||||
- 24166dc: Now only escape single dollar signs - preserve double for latex equations
|
||||
|
||||
## 0.6.73
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -30,10 +30,22 @@ class JobMetadata(BaseModel):
|
||||
class BBox(BaseModel):
|
||||
"""A bounding box."""
|
||||
|
||||
x: float = Field(description="The x-coordinate of the bounding box.")
|
||||
y: float = Field(description="The y-coordinate of the bounding box.")
|
||||
w: float = Field(description="The width of the bounding box.")
|
||||
h: float = Field(description="The height of the bounding box.")
|
||||
x: Optional[float] = Field(
|
||||
default=None,
|
||||
description="The x-coordinate of the bounding box.",
|
||||
)
|
||||
y: Optional[float] = Field(
|
||||
default=None,
|
||||
description="The y-coordinate of the bounding box.",
|
||||
)
|
||||
w: Optional[float] = Field(
|
||||
default=None,
|
||||
description="The width of the bounding box.",
|
||||
)
|
||||
h: Optional[float] = Field(
|
||||
default=None,
|
||||
description="The height of the bounding box.",
|
||||
)
|
||||
|
||||
|
||||
class PageItem(BaseModel):
|
||||
@@ -88,12 +100,16 @@ class LayoutItem(BaseModel):
|
||||
"""The layout of a page."""
|
||||
|
||||
image: str = Field(description="The name of the image containing the layout item")
|
||||
confidence: float = Field(description="The confidence of the layout item.")
|
||||
confidence: float = Field(
|
||||
default=0.0, description="The confidence of the layout item."
|
||||
)
|
||||
label: str = Field(description="The label of the layout item.")
|
||||
bbox: Optional[BBox] = Field(
|
||||
default=None, description="The bounding box of the layout item."
|
||||
)
|
||||
isLikelyNoise: bool = Field(description="Whether the layout item is likely noise.")
|
||||
isLikelyNoise: bool = Field(
|
||||
default=False, description="Whether the layout item is likely noise."
|
||||
)
|
||||
|
||||
|
||||
class ChartItem(BaseModel):
|
||||
@@ -266,18 +282,23 @@ class JobResult(BaseModel):
|
||||
if text is None:
|
||||
return None
|
||||
|
||||
def escape_dollar_signs(text: str) -> str:
|
||||
"""Escape dollar signs in text to prevent Jupyter from interpreting them as LaTeX.
|
||||
def escape_single_dollar_signs(text: str) -> str:
|
||||
"""Escape single dollar signs in text to prevent Jupyter from interpreting them as LaTeX.
|
||||
|
||||
Preserves all strings of dollar signs greater than length 1,
|
||||
especially preserving double dollar signs ($$) which denote LaTeX equations.
|
||||
|
||||
Args:
|
||||
text: The text to escape
|
||||
|
||||
Returns:
|
||||
Text with dollar signs escaped
|
||||
Text with single dollar signs escaped
|
||||
"""
|
||||
return text.replace("$", r"\$")
|
||||
# Replace single $ with \$, but preserve $$
|
||||
# Use negative lookahead and lookbehind to match $ not preceded or followed by $
|
||||
return re.sub(r"(?<!\$)\$(?!\$)", r"\$", text)
|
||||
|
||||
return escape_dollar_signs(text)
|
||||
return escape_single_dollar_signs(text)
|
||||
|
||||
def get_markdown_documents(self, split_by_page: bool = False) -> List[Document]:
|
||||
"""
|
||||
|
||||
@@ -1,5 +1,13 @@
|
||||
# llama_parse
|
||||
|
||||
## 0.6.74
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [1bf5223]
|
||||
- Updated dependencies [24166dc]
|
||||
- llama-cloud-services-py@0.6.74
|
||||
|
||||
## 0.6.73
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "llama_parse",
|
||||
"version": "0.6.73",
|
||||
"version": "0.6.74",
|
||||
"description": "",
|
||||
"main": "index.js",
|
||||
"private": false,
|
||||
|
||||
@@ -11,13 +11,13 @@ dev = [
|
||||
|
||||
[project]
|
||||
name = "llama-parse"
|
||||
version = "0.6.73"
|
||||
version = "0.6.74"
|
||||
description = "Parse files into RAG-Optimized formats."
|
||||
authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
|
||||
requires-python = ">=3.9,<4.0"
|
||||
readme = "README.md"
|
||||
license = "MIT"
|
||||
dependencies = ["llama-cloud-services>=0.6.73"]
|
||||
dependencies = ["llama-cloud-services>=0.6.74"]
|
||||
|
||||
[project.scripts]
|
||||
llama-parse = "llama_parse.cli.main:parse"
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "llama-cloud-services-py",
|
||||
"version": "0.6.73",
|
||||
"version": "0.6.74",
|
||||
"private": false,
|
||||
"license": "MIT",
|
||||
"scripts": {},
|
||||
|
||||
+1
-1
@@ -19,7 +19,7 @@ dev = [
|
||||
|
||||
[project]
|
||||
name = "llama-cloud-services"
|
||||
version = "0.6.73"
|
||||
version = "0.6.74"
|
||||
description = "Tailored SDK clients for LlamaCloud services."
|
||||
authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
|
||||
requires-python = ">=3.9,<4.0"
|
||||
|
||||
@@ -6,6 +6,40 @@ from llama_cloud_services import LlamaParse
|
||||
from llama_cloud_services.parse.types import JobResult
|
||||
|
||||
|
||||
def test_format_parse_result_markdown_for_notebook():
|
||||
"""Test the _format_markdown_for_notebook function.
|
||||
Right now, the only work it does is escape single dollar signs."""
|
||||
result = JobResult(job_id="test", file_name="test.pdf", job_result={})
|
||||
|
||||
# Test None input
|
||||
assert result._format_markdown_for_notebook(None) is None
|
||||
|
||||
# Test single dollar sign gets escaped
|
||||
assert result._format_markdown_for_notebook("This costs $5") == "This costs \\$5"
|
||||
|
||||
# Test double dollar signs are preserved (LaTeX equations)
|
||||
assert (
|
||||
result._format_markdown_for_notebook("$$x^2 + y^2 = z^2$$")
|
||||
== "$$x^2 + y^2 = z^2$$"
|
||||
)
|
||||
|
||||
# Test mixed single and double dollar signs
|
||||
text = "This costs $5, but $$E = mc^2$$ is priceless"
|
||||
expected = "This costs \\$5, but $$E = mc^2$$ is priceless"
|
||||
assert result._format_markdown_for_notebook(text) == expected
|
||||
|
||||
# Test multiple single dollar signs
|
||||
assert result._format_markdown_for_notebook("$10 and $20") == "\\$10 and \\$20"
|
||||
|
||||
# Test three or more consecutive dollar signs (preserve them)
|
||||
assert result._format_markdown_for_notebook("$$$") == "$$$"
|
||||
|
||||
# Test adjacent dollar signs with text in between
|
||||
text = "$$inline$$ and $separate"
|
||||
expected = "$$inline$$ and \\$separate"
|
||||
assert result._format_markdown_for_notebook(text) == expected
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def file_path() -> str:
|
||||
return "tests/test_files/attention_is_all_you_need.pdf"
|
||||
|
||||
Generated
+2
-2
@@ -1,5 +1,5 @@
|
||||
version = 1
|
||||
revision = 2
|
||||
revision = 3
|
||||
requires-python = ">=3.9, <4.0"
|
||||
resolution-markers = [
|
||||
"python_full_version >= '3.14'",
|
||||
@@ -1596,7 +1596,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "llama-cloud-services"
|
||||
version = "0.6.72"
|
||||
version = "0.6.73"
|
||||
source = { editable = "." }
|
||||
dependencies = [
|
||||
{ name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
|
||||
|
||||
Reference in New Issue
Block a user