Compare commits

...

3 Commits

Author SHA1 Message Date
github-actions[bot] 32c53cdf96 chore: version packages (#1046) 2025-12-04 20:43:29 -06:00
Logan 71db318fc2 add tier/version to api (#1045) 2025-12-04 20:42:17 -06:00
George He dac0f79e51 Fix sheets API client (#1032) 2025-12-03 16:39:47 -06:00
20 changed files with 20003 additions and 31540 deletions
+6
View File
@@ -1,5 +1,11 @@
# llama-cloud-services-py
## 0.6.88
### Patch Changes
- 71db318: Add tier and version
## 0.6.87
### Patch Changes
+35 -3
View File
@@ -2,7 +2,7 @@ import asyncio
import io
import os
import time
from typing import TYPE_CHECKING
from typing import Any, Dict, TYPE_CHECKING
import httpx
from llama_cloud.client import AsyncLlamaCloud
@@ -68,6 +68,8 @@ class LlamaSheets:
max_timeout: int = 300,
poll_interval: int = 5,
max_retries: int = 3,
project_id: str | None = None,
organization_id: str | None = None,
async_httpx_client: httpx.AsyncClient | None = None,
) -> None:
"""Initialize the LlamaSheets client.
@@ -78,6 +80,8 @@ class LlamaSheets:
max_timeout: Maximum time to wait for job completion in seconds
poll_interval: Interval between status checks in seconds
max_retries: Maximum number of retries for failed requests
project_id: Project ID for file operations. If not provided, will use LLAMA_CLOUD_PROJECT_ID env var
organization_id: Organization ID for file operations. If not provided, will use LLAMA_CLOUD_ORGANIZATION_ID env var
async_httpx_client: Optional custom async httpx client
"""
self.api_key = api_key or os.environ.get("LLAMA_CLOUD_API_KEY")
@@ -93,15 +97,32 @@ class LlamaSheets:
self.poll_interval = poll_interval
self.max_retries = max_retries
self.project_id = project_id or os.environ.get("LLAMA_CLOUD_PROJECT_ID")
self.organization_id = organization_id or os.environ.get(
"LLAMA_CLOUD_ORGANIZATION_ID"
)
self._async_client: httpx.AsyncClient | None = async_httpx_client
self._files_client = FileClient(
AsyncLlamaCloud(
token=self.api_key,
base_url=self.base_url,
httpx_client=async_httpx_client,
)
),
project_id=self.project_id,
organization_id=self.organization_id,
)
def _get_default_params(self) -> dict[str, str]:
"""Get default query parameters for API requests"""
params = {}
if self.project_id is not None:
params["project_id"] = self.project_id
if self.organization_id is not None:
params["organization_id"] = self.organization_id
return params
def _get_async_client(self) -> httpx.AsyncClient:
"""Get or create the async httpx client"""
if self._async_client is None:
@@ -306,6 +327,8 @@ class LlamaSheets:
"config": config.model_dump(mode="json", exclude_none=True),
}
params = self._get_default_params()
try:
async for attempt in AsyncRetrying(
stop=stop_after_attempt(self.max_retries),
@@ -318,6 +341,7 @@ class LlamaSheets:
response = await client.post(
f"{self.base_url}/api/v1/beta/sheets/jobs",
headers=self._get_headers(),
params=params,
json=payload,
)
response.raise_for_status()
@@ -347,12 +371,17 @@ class LlamaSheets:
):
with attempt:
client = self._get_async_client()
params: Dict[str, Any] = {
"include_results": include_results_metadata,
**self._get_default_params(),
}
response = await client.get(
f"{self.base_url}/api/v1/beta/sheets/jobs/{job_id}",
headers=self._get_headers(),
params={"include_results": include_results_metadata},
params=params,
)
response.raise_for_status()
return SpreadsheetJobResult.model_validate(response.json())
except Exception as e:
raise SpreadsheetAPIError(f"Failed to get job status: {e}") from e
@@ -415,6 +444,8 @@ class LlamaSheets:
# Get presigned URL
presigned_response = None
result_type_str = str(result_type)
params = self._get_default_params()
try:
async for attempt in AsyncRetrying(
stop=stop_after_attempt(self.max_retries),
@@ -427,6 +458,7 @@ class LlamaSheets:
response = await client.get(
f"{self.base_url}/api/v1/beta/sheets/jobs/{job_id}/regions/{region_id}/result/{result_type_str}",
headers=self._get_headers(),
params=params,
)
response.raise_for_status()
presigned_response = PresignedUrlResponse.model_validate(
+22
View File
@@ -654,6 +654,9 @@ class LlamaCloudIndex(BaseManagedIndex):
],
)
# Trigger a sync
client.pipelines.sync_pipeline(pipeline_id=index.pipeline.id)
doc_ids = [doc.id for doc in upserted_documents]
index.wait_for_completion(
doc_ids=doc_ids, verbose=verbose, raise_on_error=raise_on_error
@@ -738,6 +741,10 @@ class LlamaCloudIndex(BaseManagedIndex):
)
],
)
# Trigger a sync
self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
upserted_document = upserted_documents[0]
self.wait_for_completion(
doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -760,6 +767,9 @@ class LlamaCloudIndex(BaseManagedIndex):
)
],
)
# Trigger a sync
await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
upserted_document = upserted_documents[0]
await self.await_for_completion(
doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -782,6 +792,9 @@ class LlamaCloudIndex(BaseManagedIndex):
)
],
)
# Trigger a sync
self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
upserted_document = upserted_documents[0]
self.wait_for_completion(
doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -804,6 +817,9 @@ class LlamaCloudIndex(BaseManagedIndex):
)
],
)
# Trigger a sync
await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
upserted_document = upserted_documents[0]
await self.await_for_completion(
doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -827,6 +843,9 @@ class LlamaCloudIndex(BaseManagedIndex):
for doc in documents
],
)
# Trigger a sync
self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
doc_ids = [doc.id for doc in upserted_documents]
self.wait_for_completion(doc_ids=doc_ids, verbose=True, raise_on_error=True)
return [True] * len(doc_ids)
@@ -849,6 +868,9 @@ class LlamaCloudIndex(BaseManagedIndex):
for doc in documents
],
)
# Trigger a sync
await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
doc_ids = [doc.id for doc in upserted_documents]
await self.await_for_completion(
doc_ids=doc_ids, verbose=True, raise_on_error=True
+13
View File
@@ -568,6 +568,13 @@ class LlamaParse(BasePydanticReader):
default=False,
description="If set to true, the parser will include line-level bounding boxes in the result.",
)
tier: Optional[str] = Field(
default=None, description="The tier to use for the parsing job."
)
version: Optional[str] = Field(
default=None,
description="The version of the parser to use at the specified tier.",
)
# Deprecated
bounding_box: Optional[str] = Field(
@@ -1125,6 +1132,12 @@ class LlamaParse(BasePydanticReader):
if self.line_level_bounding_box is not None:
data["line_level_bounding_box"] = self.line_level_bounding_box
if self.tier is not None:
data["tier"] = self.tier
if self.version is not None:
data["version"] = self.version
# Deprecated
if self.bounding_box is not None:
data["bounding_box"] = self.bounding_box
+7
View File
@@ -1,5 +1,12 @@
# llama_parse
## 0.6.88
### Patch Changes
- Updated dependencies [71db318]
- llama-cloud-services-py@0.6.88
## 0.6.87
### Patch Changes
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "llama_parse",
"version": "0.6.87",
"version": "0.6.88",
"description": "",
"main": "index.js",
"private": false,
+2 -2
View File
@@ -11,13 +11,13 @@ dev = [
[project]
name = "llama-parse"
version = "0.6.87"
version = "0.6.88"
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>=0.6.87"]
dependencies = ["llama-cloud-services>=0.6.88"]
[project.scripts]
llama-parse = "llama_parse.cli.main:parse"
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "llama-cloud-services-py",
"version": "0.6.87",
"version": "0.6.88",
"private": false,
"license": "MIT",
"scripts": {},
+1 -1
View File
@@ -23,7 +23,7 @@ dev = [
[project]
name = "llama-cloud-services"
version = "0.6.87"
version = "0.6.88"
description = "Tailored SDK clients for LlamaCloud services."
authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
requires-python = ">=3.9,<4.0"
+6 -12
View File
@@ -44,16 +44,16 @@ class TestSpreadsheetParsingConfig:
@pytest.fixture
def sheets_client():
"""Create a LlamaSheets client for testing."""
api_key = os.getenv(
"LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
)
base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.staging.llamaindex.ai")
api_key = os.getenv("LLAMA_CLOUD_API_KEY")
base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.cloud.llamaindex.ai")
project_id = os.getenv("LLAMA_CLOUD_PROJECT_ID")
client = LlamaSheets(
api_key=api_key,
base_url=base_url,
max_timeout=300,
poll_interval=2,
project_id=project_id,
)
return client
@@ -85,10 +85,7 @@ def sample_excel_file():
@pytest.mark.skipif(
os.environ.get(
"LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
)
== "",
os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
reason="LLAMA_CLOUD_API_KEY not set",
)
@pytest.mark.asyncio
@@ -168,10 +165,7 @@ async def test_spreadsheet_extraction_e2e(
@pytest.mark.skipif(
os.environ.get(
"LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
)
== "",
os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
reason="LLAMA_CLOUD_API_KEY not set",
)
@pytest.mark.asyncio
+2 -2
View File
@@ -78,7 +78,7 @@ async def test_upload_bytes(
uploaded_file = await file_client.upload_bytes(file_bytes, external_file_id)
assert isinstance(uploaded_file, File)
expected_name = external_file_id if use_presigned_url else "upload"
expected_name = external_file_id
assert uploaded_file.name == expected_name
assert uploaded_file.external_file_id == external_file_id
@@ -100,7 +100,7 @@ async def test_upload_buffer(
uploaded_file = await file_client.upload_buffer(buffer, external_file_id, file_size)
assert isinstance(uploaded_file, File)
expected_name = external_file_id if use_presigned_url else "upload"
expected_name = external_file_id
assert uploaded_file.name == expected_name
assert uploaded_file.external_file_id == external_file_id
+6
View File
@@ -1,5 +1,11 @@
# llama-cloud-services
## 0.4.3
### Patch Changes
- 71db318: Add tier and version
## 0.4.2
### Patch Changes
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "llama-cloud-services",
"version": "0.4.2",
"version": "0.4.3",
"type": "module",
"license": "MIT",
"scripts": {
@@ -1,7 +1,7 @@
import {
addFilesToPipelineApiApiV1PipelinesPipelineIdFilesPut,
getPipelineFileStatusApiV1PipelinesPipelineIdFilesFileIdStatusGet,
listPipelineFilesApiV1PipelinesPipelineIdFilesGet,
listPipelineFiles2ApiV1PipelinesPipelineIdFiles2Get,
listProjectsApiV1ProjectsGet,
readFileContentApiV1FilesIdContentGet,
searchPipelinesApiV1PipelinesGet,
@@ -97,21 +97,20 @@ export class LLamaCloudFileService {
*/
public static async getFileUrl(pipelineId: string, filename: string) {
initService();
const { data: allPipelineFiles } =
await listPipelineFilesApiV1PipelinesPipelineIdFilesGet({
path: {
pipeline_id: pipelineId,
},
throwOnError: true,
});
const file = allPipelineFiles.find((file) => file.name === filename);
const response = await listPipelineFiles2ApiV1PipelinesPipelineIdFiles2Get({
path: {
pipeline_id: pipelineId,
},
throwOnError: true,
});
const file = response.data.files.find((file) => file.name === filename);
if (!file?.file_id) return null;
const { data: fileContent } = await readFileContentApiV1FilesIdContentGet({
path: {
id: file.file_id,
},
query: {
project_id: file.project_id,
project_id: file.project_id || null,
},
throwOnError: true,
});
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+4
View File
@@ -186,6 +186,8 @@ export class LlamaParseReader extends FileReader {
page_footer_suffix?: string | undefined;
merge_tables_across_pages_in_markdown?: boolean | undefined;
extract_printed_page_number?: boolean | undefined;
tier?: string | undefined;
version?: string | undefined;
constructor(
params: Partial<Omit<LlamaParseReader, "language" | "apiKey">> & {
@@ -383,6 +385,8 @@ export class LlamaParseReader extends FileReader {
merge_tables_across_pages_in_markdown:
this.merge_tables_across_pages_in_markdown,
extract_printed_page_number: this.extract_printed_page_number,
tier: this.tier,
version: this.version,
} satisfies {
[Key in keyof BodyUploadFileApiParsingUploadPost]-?:
| BodyUploadFileApiParsingUploadPost[Key]