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 b67fe17b787dd8af3fbe1514c51a07139efd4b47..5ce75df307596e6bd11bb0f1c62d158db623b854 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
@@ -17,6 +17,7 @@ from llama_cloud import (
ManagedIngestionStatus,
CloudDocumentCreate,
CloudDocument,
+ PipelineFileCreate,
)
from llama_index.core.base.base_query_engine import BaseQueryEngine
@@ -455,6 +456,67 @@ class LlamaCloudIndex(BaseManagedIndex):
verbose=verbose, raise_on_partial_success=False
)
+ def upload_file(
+ self,
+ file_path: str,
+ resource_info: Optional[Dict[str, Any]] = None,
+ verbose: bool = False,
+ ) -> str:
+ """Upload a file to the index."""
+ with open(file_path, "rb") as f:
+ file = self._client.files.upload_file(
+ project_id=self._get_project_id(), upload_file=f
+ )
+ if verbose:
+ print(f"Uploaded file {file.id} with name {file.name}")
+ if resource_info:
+ self._client.files.update(file_id=file.id, request=resource_info)
+ # Add file to pipeline
+ pipeline_id = self._get_pipeline_id()
+ pipeline_file_create = PipelineFileCreate(file_id=file.id)
+ self._client.pipelines.add_files_to_pipeline(
+ pipeline_id=pipeline_id, request=[pipeline_file_create]
+ )
+
+ self._wait_for_pipeline_ingestion(
+ verbose=verbose, raise_on_partial_success=False
+ )
+ return file.id
+
+ def upload_file_from_url(
+ self,
+ file_name: str,
+ url: str,
+ proxy_url: Optional[str] = None,
+ request_headers: Optional[Dict[str, str]] = None,
+ verify_ssl: bool = True,
+ follow_redirects: bool = True,
+ verbose: bool = False,
+ ) -> str:
+ """Upload a file from a URL to the index."""
+ file = self._client.files.upload_file_from_url(
+ project_id=self._get_project_id(),
+ name=file_name,
+ url=url,
+ proxy_url=proxy_url,
+ request_headers=request_headers,
+ verify_ssl=verify_ssl,
+ follow_redirects=follow_redirects,
+ )
+ if verbose:
+ print(f"Uploaded file {file.id} with ID {file.id}")
+ # Add file to pipeline
+ pipeline_id = self._get_pipeline_id()
+ pipeline_file_create = PipelineFileCreate(file_id=file.id)
+ self._client.pipelines.add_files_to_pipeline(
+ pipeline_id=pipeline_id, request=[pipeline_file_create]
+ )
+
+ self._wait_for_pipeline_ingestion(
+ verbose=verbose, raise_on_partial_success=False
+ )
+ return file.id
+
# Nodes related methods (not implemented for LlamaCloudIndex)
def _insert(self, nodes: Sequence[BaseNode], **insert_kwargs: Any) -> None:
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 91df56a18b8a8353c272ef635b881dba4efa4f88..9810d623c0c122c7f4d173a3bdb99a2ca64ea08b 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
@@ -34,11 +34,11 @@ exclude = ["**/BUILD"]
license = "MIT"
name = "llama-index-indices-managed-llama-cloud"
readme = "README.md"
-version = "0.4.0"
+version = "0.4.1"
[tool.poetry.dependencies]
python = ">=3.8.1,<4.0"
-llama-cloud = ">=0.0.11"
+llama-cloud = ">=0.1.5"
llama-index-core = "^0.11.13.post1"
[tool.poetry.group.dev.dependencies]
diff --git a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/tests/test_indices_managed_llama_cloud.py b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/tests/test_indices_managed_llama_cloud.py
index ad8f19d747c52fcd65c3cb539a0298170a5b9d6b..d1f3887e59e1a13c05db5983c3bcff2dce75b1a8 100644
--- a/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/tests/test_indices_managed_llama_cloud.py
+++ b/llama-index-integrations/indices/llama-index-indices-managed-llama-cloud/tests/test_indices_managed_llama_cloud.py
@@ -1,4 +1,5 @@
from typing import Optional
+import tempfile
from llama_index.core.indices.managed.base import BaseManagedIndex
from llama_index.indices.managed.llama_cloud import LlamaCloudIndex
from llama_index.core.schema import Document
@@ -18,7 +19,7 @@ def test_class():
@pytest.mark.skipif(
- not base_url or not api_key, reason="No platform base url or api keyset"
+ not base_url or not api_key, reason="No platform base url or api key set"
)
@pytest.mark.skipif(not openai_api_key, reason="No openai api key set")
@pytest.mark.integration()
@@ -40,7 +41,7 @@ def test_retrieve():
@pytest.mark.parametrize("organization_id", [None, organization_id])
@pytest.mark.skipif(
- not base_url or not api_key, reason="No platform base url or api keyset"
+ not base_url or not api_key, reason="No platform base url or api key set"
)
@pytest.mark.skipif(not openai_api_key, reason="No openai api key set")
@pytest.mark.integration()
@@ -101,3 +102,68 @@ def test_documents_crud(organization_id: Optional[str]):
docs = index.ref_doc_info
assert len(docs) == 2
assert "3" not in docs
+
+
+@pytest.mark.skipif(
+ not base_url or not api_key, reason="No platform base url or api key set"
+)
+@pytest.mark.skipif(not openai_api_key, reason="No openai api key set")
+@pytest.mark.integration()
+def test_upload_file():
+ os.environ["OPENAI_API_KEY"] = openai_api_key
+ index = LlamaCloudIndex(
+ name="test", # assumes this pipeline exists
+ project_name="Default",
+ api_key=api_key,
+ base_url=base_url,
+ )
+
+ # Create a temporary file to upload
+ with tempfile.NamedTemporaryFile(delete=False, suffix=".txt") as temp_file:
+ temp_file.write(b"Sample content for testing upload.")
+ temp_file_path = temp_file.name
+
+ try:
+ # Upload the file
+ file_id = index.upload_file(temp_file_path, verbose=True)
+ assert file_id is not None
+
+ # Verify the file is part of the index
+ docs = index.ref_doc_info
+ temp_file_name = os.path.basename(temp_file_path)
+ assert any(
+ temp_file_name == doc.metadata.get("file_name") for doc in docs.values()
+ )
+
+ finally:
+ # Clean up the temporary file
+ os.remove(temp_file_path)
+
+
+@pytest.mark.skipif(
+ not base_url or not api_key, reason="No platform base url or api key set"
+)
+@pytest.mark.skipif(not openai_api_key, reason="No openai api key set")
+@pytest.mark.integration()
+def test_upload_file_from_url():
+ os.environ["OPENAI_API_KEY"] = openai_api_key
+ index = LlamaCloudIndex(
+ name="test", # assumes this pipeline exists
+ project_name="Default",
+ api_key=api_key,
+ base_url=base_url,
+ )
+
+ # Define a URL to a file for testing
+ test_file_url = "https://www.google.com/robots.txt"
+ test_file_name = "google_robots.txt"
+
+ # Upload the file from the URL
+ file_id = index.upload_file_from_url(
+ file_name=test_file_name, url=test_file_url, verbose=True
+ )
+ assert file_id is not None
+
+ # Verify the file is part of the index
+ docs = index.ref_doc_info
+ assert any(test_file_name == doc.metadata.get("file_name") for doc in docs.values())