Retrieve context from an assistant
Retrieve context snippets from an assistant to use as part of RAG or any agentic flow.
For guidance and examples, see Retrieve context snippets.
PINECONE_API_KEY="YOUR_API_KEY"
ASSISTANT_NAME="example-assistant"
curl "https://prod-1-data.ke.pinecone.io/assistant/chat/$ASSISTANT_NAME/context" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "accept: application/json" \
-H "Content-Type: application/json" \
-H "X-Pinecone-Api-Version: 2025-10" \
-d '{
"query": "Who is the CFO of Netflix?"
}'{
"snippets":
[
{
"type":"text",
"content":"EXHIBIT 31.3\nCERTIFICATION OF CHIEF FINANCIAL OFFICER\nPURSUANT TO SECTION 302 OF THE SARBANES-OXLEY ACT OF 2002\nI, Spencer Neumann, certify that: ...",
"score":0.9960699,
"reference":
{
"type":"pdf",
"file":
{
"status":"Available","id":"e6034e51-0bb9-4926-84c6-70597dbd07a7",
"name":"Netflix-10-K-01262024.pdf",
"size":1073470,
"metadata":null,
"updated_on":"2024-11-21T22:59:10.426001030Z",
"created_on":"2024-11-21T22:58:35.879120257Z",
"percent_done":1.0,
"signed_url":"https://storage.googleapis.com...",
"error_message":null
},
"pages":[78]
}
},
{
"type":"text",
"content":"EXHIBIT 32.1\n..."
...POST /chat/{assistant_name}/context
Authorizations
Section titled “Authorizations”Api-KeystringrequiredPinecone API Key
Headers
Section titled “Headers”X-Pinecone-Api-VersionstringrequiredRequired date-based version header
Path Parameters
Section titled “Path Parameters”assistant_namestringrequiredThe name of the assistant to be described.
The desired configuration to retrieve context from an assistant.
query?stringThe query that is used to generate the context. Exactly one of query or messages should be provided.
filter?objectOptionally filter which documents can be retrieved using the following metadata fields.
messages?object[]The list of messages to use for generating the context. Exactly one of query or messages should be provided.
Show child attributes
role?stringRole of the message such as 'user' or 'assistant'
content?stringContent of the message
top_k?integerThe maximum number of context snippets to return. Default is 16. Maximum is 64.
Example: 20
snippet_size?integerThe maximum context snippet size. Default is 2048 tokens. Minimum is 512 tokens. Maximum is 8192 tokens.
Example: 4096
multimodal?booleanWhether or not to retrieve image-related context snippets. If false, only text snippets are returned.
include_binary_content?booleanIf image-related context snippets are returned, this field determines whether or not they should include base64 image data. If false, only the image captions are returned. Only available when multimodal=true.
Response
Section titled “Response”200 — Context retrieval process successful.
The response format containing the context from an assistant.
id?stringsnippetsobject[]requiredShow child attributes
typestringrequiredThe type of context snippet.
contentstringrequiredscorenumberrequiredreferenceobjectrequiredRepresents a reference to a part of a text document.
Show child attributes
typestringrequiredThe type of reference. Always 'text'.
fileobjectrequiredThe response format for a successful file upload request.
Show child attributes
namestringrequiredidstringrequiredmetadata?object | nullcreated_on?stringupdated_on?stringstatus?stringThe current state of the uploaded file. Possible values: - Processing: File is being processed (parsed, chunked, embedded) - Available: Processing completed successfully; file is ready for use - Deleting: Deletion has been initiated but not yet completed - ProcessingFailed: Processing failed with an error Note: Once a file is deleted, the API returns 404 Not Found instead of a file object.
percent_done?number | nullThe percentage of the file that has been processed
signed_url?string | nullExample: https://storage.googleapis.com/bucket/file.pdf?...
A signed URL that provides temporary, read-only access to the underlying file. Anyone with the link can access the file, so treat it as sensitive data. Expires after a short time.
error_message?string | nullA message describing any error during file processing. Provided only if an error occurs.
multimodal?booleanIndicates whether the file was processed as multimodal.
usageobjectrequiredDescribes the usage of a chat completion.
Show child attributes
prompt_tokens?integercompletion_tokens?integertotal_tokens?integer