POST
/
assistant
/
chat
/
{assistant_name}
/
chat
/
completions

This feature is in public preview.

Authorizations

Api-Key
string
headerrequired

Pinecone API Key

Path Parameters

assistant_name
string
required

The name of the assistant to be described.

Body

application/json

The list of queries / chat's to chat an assistant

messages
object[]
required
stream
boolean
default: false

If false, the assistant will return a single JSON response. If true, the assistant will return a stream of responses.

model
enum<string>
default: gpt-4o

The large language model to use for answer generation

Available options:
gpt-4o,
claude-3-5-sonnet
filter
object

Optionally filter which documents can be used in this query.

Response

200 - application/json

The ChatCompletionModel describes the response format of a chat request

id
string
choices
object[]
model
string
usage
object

The UsageModel describes the usage of a chat completion