From cd70d3b47807fb5478bd9b7e57617737fcd512f7 Mon Sep 17 00:00:00 2001
From: George He <georgewho96@gmail.com>
Date: Sun, 16 Feb 2025 13:11:56 -0800
Subject: [PATCH] Improve error logs for llamacloud indices (#17827)
---
.../indices/managed/llama_cloud/base.py | 23 ++++++++++++++-----
.../pyproject.toml | 2 +-
2 files changed, 18 insertions(+), 7 deletions(-)
diff --git a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/base.py b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/base.py
index c3cac40b3..9da112316 100644
--- a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/base.py
+++ b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/base.py
@@ -12,6 +12,7 @@ from typing import Any, List, Optional, Sequence, Type
from urllib.parse import quote_plus
from llama_cloud import (
+ ManagedIngestionStatusResponse,
PipelineCreate,
PipelineCreateEmbeddingConfig,
PipelineCreateTransformConfig,
@@ -165,31 +166,41 @@ class LlamaCloudIndex(BaseManagedIndex):
self,
verbose: bool = False,
raise_on_partial_success: bool = False,
- ) -> None:
+ sleep_interval: float = 0.5,
+ ) -> Optional[ManagedIngestionStatusResponse]:
+ if sleep_interval < 0.5:
+ # minimum sleep interval at 0.5 seconds to prevent rate-limiting
+ sleep_interval = 0.5
if verbose:
- print("Syncing pipeline: ", end="")
+ print(f"Syncing pipeline {self.pipeline.id}: ", end="")
is_done = False
+ status_response: Optional[ManagedIngestionStatusResponse] = None
while not is_done:
- status = self._client.pipelines.get_pipeline_status(
+ status_response = self._client.pipelines.get_pipeline_status(
pipeline_id=self.pipeline.id
- ).status
+ )
+ status = status_response.status
if status == ManagedIngestionStatus.ERROR or (
raise_on_partial_success
and status == ManagedIngestionStatus.PARTIAL_SUCCESS
):
- raise ValueError(f"Pipeline ingestion failed for {self.pipeline.id}")
+ error_details = status_response.json()
+ raise ValueError(
+ f"Pipeline ingestion failed for {self.pipeline.id}. Error details: {error_details}"
+ )
elif status in [
ManagedIngestionStatus.NOT_STARTED,
ManagedIngestionStatus.IN_PROGRESS,
]:
if verbose:
print(".", end="")
- time.sleep(0.5)
+ time.sleep(sleep_interval)
else:
is_done = True
if verbose:
print("Done!")
+ return status_response
def _wait_for_file_ingestion(
self,
diff --git a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/pyproject.toml b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/pyproject.toml
index b0a344c59..f967eca32 100644
--- a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/pyproject.toml
+++ b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/pyproject.toml
@@ -34,7 +34,7 @@ exclude = ["**/BUILD"]
license = "MIT"
name = "llama-index-indices-managed-llama-cloud"
readme = "README.md"
-version = "0.6.4"
+version = "0.6.5"
[tool.poetry.dependencies]
python = ">=3.9,<4.0"
--
GitLab