mirror of
https://github.com/run-llama/llama_cloud_services.git
synced 2026-07-21 03:55:22 -04:00
Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| ebf3b6b630 | |||
| f14a4b2101 | |||
| 850728a190 | |||
| 62cf12d6eb | |||
| 253ee61463 |
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
After Width: | Height: | Size: 580 KiB |
+53
-1
@@ -154,6 +154,31 @@ class LlamaParse(BasePydanticReader):
|
||||
custom_client: Optional[httpx.AsyncClient] = Field(
|
||||
default=None, description="A custom HTTPX client to use for sending requests."
|
||||
)
|
||||
disable_ocr: bool = Field(
|
||||
default=False,
|
||||
description="Disable the OCR on the document. LlamaParse will only extract the copyable text from the document.",
|
||||
)
|
||||
# Coming Soon
|
||||
# annotate_links: bool = Field(
|
||||
# default=False,
|
||||
# description="Annotate links found in the document to extract their URL.",
|
||||
# )
|
||||
webhook_url: Optional[str] = Field(
|
||||
default=None,
|
||||
description="A URL that needs to be called at the end of the parsing job.",
|
||||
)
|
||||
azure_openai_deployment_name: Optional[str] = Field(
|
||||
default=None, description="Azure Openai Deployment Name"
|
||||
)
|
||||
azure_openai_endpoint: Optional[str] = Field(
|
||||
default=None, description="Azure Openai Endpoint"
|
||||
)
|
||||
azure_openai_api_version: Optional[str] = Field(
|
||||
default=None, description="Azure Openai API Version"
|
||||
)
|
||||
azure_openai_key: Optional[str] = Field(
|
||||
default=None, description="Azure Openai Key"
|
||||
)
|
||||
|
||||
@field_validator("api_key", mode="before", check_fields=True)
|
||||
@classmethod
|
||||
@@ -239,6 +264,8 @@ class LlamaParse(BasePydanticReader):
|
||||
"use_vendor_multimodal_model": self.use_vendor_multimodal_model,
|
||||
"vendor_multimodal_model_name": self.vendor_multimodal_model_name,
|
||||
"take_screenshot": self.take_screenshot,
|
||||
"disable_ocr": self.disable_ocr,
|
||||
# "annotate_links": self.annotate_links,
|
||||
}
|
||||
|
||||
# only send page separator to server if it is not None
|
||||
@@ -258,6 +285,22 @@ class LlamaParse(BasePydanticReader):
|
||||
if self.target_pages is not None:
|
||||
data["target_pages"] = self.target_pages
|
||||
|
||||
if self.webhook_url is not None:
|
||||
data["webhook_url"] = self.webhook_url
|
||||
|
||||
# Azure OpenAI
|
||||
if self.azure_openai_deployment_name is not None:
|
||||
data["azure_openai_deployment_name"] = self.azure_openai_deployment_name
|
||||
|
||||
if self.azure_openai_endpoint is not None:
|
||||
data["azure_openai_endpoint"] = self.azure_openai_endpoint
|
||||
|
||||
if self.azure_openai_api_version is not None:
|
||||
data["azure_openai_api_version"] = self.azure_openai_api_version
|
||||
|
||||
if self.azure_openai_key is not None:
|
||||
data["azure_openai_key"] = self.azure_openai_key
|
||||
|
||||
try:
|
||||
async with self.client_context() as client:
|
||||
response = await client.post(
|
||||
@@ -308,7 +351,8 @@ class LlamaParse(BasePydanticReader):
|
||||
continue
|
||||
|
||||
# Allowed values "PENDING", "SUCCESS", "ERROR", "CANCELED"
|
||||
status = result.json()["status"]
|
||||
result_json = result.json()
|
||||
status = result_json["status"]
|
||||
if status == "SUCCESS":
|
||||
parsed_result = await client.get(result_url, headers=headers)
|
||||
return parsed_result.json()
|
||||
@@ -320,6 +364,14 @@ class LlamaParse(BasePydanticReader):
|
||||
print(".", end="", flush=True)
|
||||
|
||||
await asyncio.sleep(self.check_interval)
|
||||
else:
|
||||
error_code = result_json.get("error_code", "No error code found")
|
||||
error_message = result_json.get(
|
||||
"error_message", "No error message found"
|
||||
)
|
||||
|
||||
exception_str = f"Job ID: {job_id} failed with status: {status}, Error code: {error_code}, Error message: {error_message}"
|
||||
raise Exception(exception_str)
|
||||
|
||||
async def _aload_data(
|
||||
self,
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
|
||||
|
||||
[tool.poetry]
|
||||
name = "llama-parse"
|
||||
version = "0.5.6"
|
||||
version = "0.5.8"
|
||||
description = "Parse files into RAG-Optimized formats."
|
||||
authors = ["Logan Markewich <logan@llamaindex.ai>"]
|
||||
license = "MIT"
|
||||
|
||||
Reference in New Issue
Block a user