From 77289be4bd298d5efce414a6be4051410a44dfdd Mon Sep 17 00:00:00 2001
From: Sourabh Desai <sourabhdesai@gmail.com>
Date: Sun, 16 Feb 2025 13:13:49 -0800
Subject: [PATCH] include file & page metadata when returning image node from
llamacloud retriever (#17823)
---
.../llama_index/indices/managed/llama_cloud/api_utils.py | 9 +++++++--
.../pyproject.toml | 2 +-
2 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/api_utils.py b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/api_utils.py
index 63fdf79a04..e90b68b9a5 100644
--- a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/api_utils.py
+++ b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/llama_index/indices/managed/llama_cloud/api_utils.py
@@ -1,4 +1,4 @@
-from typing import Optional, Tuple, Union
+from typing import Any, Optional, Tuple, Union, Dict
import urllib.parse
from httpx import Request
@@ -197,8 +197,13 @@ async def aimage_nodes_to_node_with_score(
image_bytes_list = await run_jobs(tasks)
for image_bytes, raw_image_node in zip(image_bytes_list, raw_image_nodes):
image_base64 = base64.b64encode(image_bytes).decode("utf-8")
+ image_node_metadata: Dict[str, Any] = {
+ "file_id": raw_image_node.node.file_id,
+ "page_index": raw_image_node.node.page_index,
+ }
image_node_with_score = NodeWithScore(
- node=ImageNode(image=image_base64), score=raw_image_node.score
+ node=ImageNode(image=image_base64, metadata=image_node_metadata),
+ score=raw_image_node.score,
)
image_nodes.append(image_node_with_score)
return image_nodes
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 f967eca322..298588c94c 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 = "0.6.5"
+version = "0.6.6"
[tool.poetry.dependencies]
python = ">=3.9,<4.0"
--
GitLab