Files
Upload file to assistant
Assistants
Evaluation
Context snippets
Admin
- API keys
- Projects
- Service accounts
Architecture
Files
Upload file to assistant
Upload a file to the specified assistant.
For guidance and examples, see Manage files.
POST
/
files
/
{assistant_name}
# To use the Python SDK, install the plugin:
# pip install --upgrade pinecone pinecone-plugin-assistant
from pinecone import Pinecone
pc = Pinecone(api_key="YOUR_API_KEY")
# Get the assistant.
assistant = pc.assistant.Assistant(
assistant_name="example-assistant",
)
# Upload a file from a local path.
response = assistant.upload_file(
file_path="/Users/jdoe/Downloads/example_file.txt",
metadata={"published": "2024-01-01", "document_type": "manuscript"},
timeout=None
)
# Upload from an in-memory binary stream.
from io import BytesIO
# Create a BytesIO stream with some content.
md_text = "# Title\n\ntext"
stream = BytesIO(md_text.encode("utf-8"))
# Upload the stream.
response_bytes_stream = assistant.upload_bytes_stream(
stream=stream,
filename="example_file.md",
timeout=None
)
{
"name": "example-file.txt",
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"metadata": "{ 'published': '2024-01-01', 'document_type': 'manuscript' }",
"created_on": "2023-11-07T05:31:56Z",
"updated_on": "2023-11-07T05:31:56Z",
"status": "Processing",
"percent_done": 50,
"signed_url": "https://storage.googleapis.com/bucket/file.pdf",
"error_message": "<string>"
}
# To use the Python SDK, install the plugin:
# pip install --upgrade pinecone pinecone-plugin-assistant
from pinecone import Pinecone
pc = Pinecone(api_key="YOUR_API_KEY")
# Get the assistant.
assistant = pc.assistant.Assistant(
assistant_name="example-assistant",
)
# Upload a file from a local path.
response = assistant.upload_file(
file_path="/Users/jdoe/Downloads/example_file.txt",
metadata={"published": "2024-01-01", "document_type": "manuscript"},
timeout=None
)
# Upload from an in-memory binary stream.
from io import BytesIO
# Create a BytesIO stream with some content.
md_text = "# Title\n\ntext"
stream = BytesIO(md_text.encode("utf-8"))
# Upload the stream.
response_bytes_stream = assistant.upload_bytes_stream(
stream=stream,
filename="example_file.md",
timeout=None
)
{
"name": "example-file.txt",
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"metadata": "{ 'published': '2024-01-01', 'document_type': 'manuscript' }",
"created_on": "2023-11-07T05:31:56Z",
"updated_on": "2023-11-07T05:31:56Z",
"status": "Processing",
"percent_done": 50,
"signed_url": "https://storage.googleapis.com/bucket/file.pdf",
"error_message": "<string>"
}
Authorizations
Pinecone API Key
Path Parameters
The name of the assistant to upload files to.
Query Parameters
Optional JSON-encoded metadata for files.
Body
multipart/form-data
The desired file to be uploaded and processed into the assistant.
The body is of type object
.
Response
200
application/json
File upload has been accepted.
AssistantFileModel is the response format to a successful file upload request.
Was this page helpful?
# To use the Python SDK, install the plugin:
# pip install --upgrade pinecone pinecone-plugin-assistant
from pinecone import Pinecone
pc = Pinecone(api_key="YOUR_API_KEY")
# Get the assistant.
assistant = pc.assistant.Assistant(
assistant_name="example-assistant",
)
# Upload a file from a local path.
response = assistant.upload_file(
file_path="/Users/jdoe/Downloads/example_file.txt",
metadata={"published": "2024-01-01", "document_type": "manuscript"},
timeout=None
)
# Upload from an in-memory binary stream.
from io import BytesIO
# Create a BytesIO stream with some content.
md_text = "# Title\n\ntext"
stream = BytesIO(md_text.encode("utf-8"))
# Upload the stream.
response_bytes_stream = assistant.upload_bytes_stream(
stream=stream,
filename="example_file.md",
timeout=None
)
{
"name": "example-file.txt",
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"metadata": "{ 'published': '2024-01-01', 'document_type': 'manuscript' }",
"created_on": "2023-11-07T05:31:56Z",
"updated_on": "2023-11-07T05:31:56Z",
"status": "Processing",
"percent_done": 50,
"signed_url": "https://storage.googleapis.com/bucket/file.pdf",
"error_message": "<string>"
}