parallex 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

parallex/parallex.py

@@ -21,9 +21,9 @@ async def parallex(
     model: str,
     pdf_source_url: str,
     post_process_callable: Optional[Callable[..., None]] = None,
-    concurrency: int = 20,
-    prompt_text: str = DEFAULT_PROMPT,
-    log_level: str = "ERROR",
+    concurrency: Optional[int] = 20,
+    prompt_text: Optional[str] = DEFAULT_PROMPT,
+    log_level: Optional[str] = "ERROR",
 ) -> ParallexCallableOutput:
     setup_logger(log_level)
     with tempfile.TemporaryDirectory() as temp_directory:

parallex-0.1.2.dist-info/METADATA

@@ -0,0 +1,95 @@
+Metadata-Version: 2.1
+Name: parallex
+Version: 0.1.2
+Summary: PDF to markdown using Azure OpenAI batch processing
+Home-page: https://github.com/Summed-AI/parallex
+Author: Jeff Hostetler
+Author-email: jeff@summed.ai
+Requires-Python: >=3.12,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: aiologger (>=0.7.0,<0.8.0)
+Requires-Dist: asyncio (>=3.4.3,<4.0.0)
+Requires-Dist: httpx (>=0.27.2,<0.28.0)
+Requires-Dist: openai (>=1.54.4,<2.0.0)
+Requires-Dist: pdf2image (>=1.17.0,<2.0.0)
+Requires-Dist: pydantic (>=2.9.2,<3.0.0)
+Project-URL: Repository, https://github.com/Summed-AI/parallex
+Description-Content-Type: text/markdown
+
+# Parallex
+
+### What it does
+- Converts PDF into images
+- Makes requests to Azure OpenAI to covert the images to markdown using Batch API
+  - [Azure OpenAPI Batch](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/batch?tabs=standard-input%2Cpython-secure&pivots=programming-language-python)
+  - [OpenAPI Batch](https://platform.openai.com/docs/guides/batch)
+- Polls for batch completion and then coverts AI responses in structured output based on the page of the corresponding PDF
+- Post batch processing to do what you wish with the resulting markdown
+
+### Requirements
+Parallex uses `graphicsmagick` for the conversion of PDF to images. 
+```bash
+brew install graphicsmagick
+```
+
+
+### Example usage
+
+```python
+import os
+from parallex.models.parallex_callable_output import ParallexCallableOutput
+from parallex.parallex import parallex
+
+os.environ["AZURE_OPENAI_API_KEY"] = "key"
+os.environ["AZURE_OPENAI_ENDPOINT"] = "your-endpoint.com"
+os.environ["AZURE_OPENAI_API_VERSION"] = "deployment_version"
+os.environ["AZURE_OPENAI_API_DEPLOYMENT"] = "deployment_name"
+
+model = "gpt-4o"
+
+async def some_operation(file_url: str) -> None:
+  response_data: ParallexCallableOutput = await parallex(
+    model=model,
+    pdf_source_url=file_url,
+    post_process_callable=example_post_process, # Optional
+    concurrency=2, # Optional
+    prompt_text="Turn images into markdown", # Optional
+    log_level="ERROR" # Optional
+  )
+  pages = response_data.pages
+
+def example_post_process(output: ParallexCallableOutput) -> None:
+    file_name = output.file_name
+    pages = output.pages
+    for page in pages:
+        markdown_for_page = page.output_content
+        pdf_page_number = page.page_number
+        
+```
+
+Responses have the following structure;
+```python
+class ParallexCallableOutput(BaseModel):
+    file_name: str = Field(description="Name of file that is processed")
+    pdf_source_url: str = Field(description="Given URL of the source of output")
+    trace_id: UUID = Field(description="Unique trace for each file")
+    pages: list[PageResponse] = Field(description="List of PageResponse objects")
+
+class PageResponse(BaseModel):
+    output_content: str = Field(description="Markdown generated for the page")
+    page_number: int = Field(description="Page number of the associated PDF")
+```
+
+### Default prompt is 
+```python
+"""
+    Convert the following PDF page to markdown.
+    Return only the markdown with no explanation text.
+    Leave out any page numbers and redundant headers or footers.
+    Do not include any code blocks (e.g. "```markdown" or "```") in the response.
+    If unable to parse, return an empty string.
+"""
+```
+

{parallex-0.1.0.dist-info → parallex-0.1.2.dist-info}/RECORD

@@ -12,10 +12,10 @@ parallex/models/page_response.py,sha256=KADCAV3XnkqWm-q_FBCfbt5nqDbiHg9MroZvFXaB
 parallex/models/parallex_callable_output.py,sha256=CkJKA8mwsc5olNnG1K6nrWUu4xTkJvp8bp3SSPQEX5c,465
 parallex/models/raw_file.py,sha256=Nlv6u_jlDCXDgU2_Ff7DRbDCx27pB1NZugNhEoaBMQU,483
 parallex/models/upload_batch.py,sha256=jrnds9ryXg9drL4TF8TGimMVTCDfKaWsBzFv_ed0i88,2068
-parallex/parallex.py,sha256=2XXmG54eXtXnw2ElC12zjbWDnwDIHPgzKY1ktP8V93M,4472
+parallex/parallex.py,sha256=RvSDNyjrE7Fd3LuatEt18_1sR_btPJ-i6uxjNr_dGh0,4502
 parallex/utils/constants.py,sha256=c6i_-OSfCXAzW9ILzddSSHfldqHnsPEID3G3VYGYXUg,362
 parallex/utils/logger.py,sha256=5dpTogztRq4NCgYWnbbkFNx3V2sFCN-Mtoagwj8i18Q,505
-parallex-0.1.0.dist-info/LICENSE,sha256=wPwCqGrisXnEcpaUxSO79C2mdOUTbtjhLjyy8mVW6p8,1046
-parallex-0.1.0.dist-info/METADATA,sha256=ICDxk_FnofGhJgeGXv_g-awaZm_g4zU23PkfuXOndNs,1485
-parallex-0.1.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-parallex-0.1.0.dist-info/RECORD,,
+parallex-0.1.2.dist-info/LICENSE,sha256=wPwCqGrisXnEcpaUxSO79C2mdOUTbtjhLjyy8mVW6p8,1046
+parallex-0.1.2.dist-info/METADATA,sha256=MJ1bOEQ2MXvKhha6y1ehwMFzqf54DBKVuMxkipPM0tY,3393
+parallex-0.1.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+parallex-0.1.2.dist-info/RECORD,,

parallex-0.1.0.dist-info/METADATA

@@ -1,42 +0,0 @@
-Metadata-Version: 2.1
-Name: parallex
-Version: 0.1.0
-Summary: 
-Author: Jeff Hostetler
-Author-email: jeff@summed.ai
-Requires-Python: >=3.12,<4.0
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: aiologger (>=0.7.0,<0.8.0)
-Requires-Dist: asyncio (>=3.4.3,<4.0.0)
-Requires-Dist: httpx (>=0.27.2,<0.28.0)
-Requires-Dist: openai (>=1.54.4,<2.0.0)
-Requires-Dist: pdf2image (>=1.17.0,<2.0.0)
-Requires-Dist: pydantic (>=2.9.2,<3.0.0)
-Description-Content-Type: text/markdown
-
-# Parallex
-
-### What it does
-- Converts file into images
-- Makes requests to OpenAI to covert the images to markdown
-  - [Azure OpenAPI Batch](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/batch?tabs=standard-input%2Cpython-secure&pivots=programming-language-python)
-  - [OpenAPI Batch](https://platform.openai.com/docs/guides/batch)
-- Post batch processing to do what you wish with the resulting markdown
-
-
-# Notes for us as we build
-### Poetry
-- Using [poetry](https://python-poetry.org/docs/) for dependency management
-- add dependency `poetry add pydantic`
-- add dev dependency `poetry add --group dev black`
-- run main script `poetry run python main.py`
-- run dev commands `poetry run black parallex`
-
-
-# General behavior
-- parallex takes args to do things with file
-- parallex takes args to specify llm model
-- parallex takes a callable to execute once batch process is "ready"
-