# pip install --upgrade pinecone
import os
from pinecone import Pinecone
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
response = pc.assistants.chat_completions(
assistant_name="example-assistant",
messages=[{"role": "user", "content": "What is the maximum height of a red pine?"}],
)
print(response.choices[0].message.content)
# pip install --upgrade pinecone
import os
from pinecone import Pinecone
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
stream = pc.assistants.chat_completions(
assistant_name="example-assistant",
messages=[{"role": "user", "content": "What is the maximum height of a red pine?"}],
stream=True,
)
for chunk in stream:
for choice in chunk.choices:
if choice.delta.content:
print(choice.delta.content, end="", flush=True)
// npm install @pinecone-database/pinecone
import { Pinecone } from '@pinecone-database/pinecone';
// Reads PINECONE_API_KEY from the environment
const pc = new Pinecone();
const assistant = pc.assistant({ name: 'example-assistant' });
const response = await assistant.chatCompletion({
messages: [{ role: 'user', content: 'What is the maximum height of a red pine?' }],
});
console.log(response.choices?.[0]?.message?.content);
// npm install @pinecone-database/pinecone
import { Pinecone } from '@pinecone-database/pinecone';
// Reads PINECONE_API_KEY from the environment
const pc = new Pinecone();
const assistant = pc.assistant({ name: 'example-assistant' });
const stream = await assistant.chatCompletionStream({
messages: [{ role: 'user', content: 'What is the maximum height of a red pine?' }],
});
for await (const chunk of stream) {
for (const choice of chunk.choices) {
if (choice.delta.content) {
process.stdout.write(choice.delta.content);
}
}
}
PINECONE_API_KEY="YOUR_API_KEY"
ASSISTANT_NAME="example-assistant"
curl "https://prod-1-data.ke.pinecone.io/assistant/chat/$ASSISTANT_NAME/chat/completions" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{
"role": "user",
"content": "What is the maximum height of a red pine?"
}
]
}'
PINECONE_API_KEY="YOUR_API_KEY"
ASSISTANT_NAME="example-assistant"
curl "https://prod-1-data.ke.pinecone.io/assistant/chat/$ASSISTANT_NAME/chat/completions" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Pinecone-Api-Version: 2026-07" \
-d '{
"messages": [
{
"role": "user",
"content": "What is the maximum height of a red pine?"
}
],
"stream": true
}'
{
"id": "<string>",
"choices": [
{
"finish_reason": "<string>",
"index": 123,
"message": {
"role": "<string>",
"content": "<string>"
}
}
],
"model": "<string>",
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"code": "INVALID_ARGUMENT",
"message": "Uploaded file can only currently be either a pdf or txt file"
},
"status": 400
}{
"error": {
"code": "UNAUTHENTICATED",
"message": "Invalid API key."
},
"status": 401
}{
"error": {
"code": "NOT_FOUND",
"message": "Assistant \"example-assistant\" not found."
},
"status": 404
}{
"error": {
"code": "UNKNOWN",
"message": "Internal server error"
},
"status": 500
}Chat
Chat through an OpenAI-compatible interface
Chat with an assistant. This endpoint is based on the OpenAI Chat Completion API, a commonly used and adopted API.
It is useful if you need inline citations or OpenAI-compatible responses, but has limited functionality compared to the standard chat interface.
For guidance and examples, see Chat with an assistant.
POST
/
chat
/
{assistant_name}
/
chat
/
completions
# pip install --upgrade pinecone
import os
from pinecone import Pinecone
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
response = pc.assistants.chat_completions(
assistant_name="example-assistant",
messages=[{"role": "user", "content": "What is the maximum height of a red pine?"}],
)
print(response.choices[0].message.content)
# pip install --upgrade pinecone
import os
from pinecone import Pinecone
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
stream = pc.assistants.chat_completions(
assistant_name="example-assistant",
messages=[{"role": "user", "content": "What is the maximum height of a red pine?"}],
stream=True,
)
for chunk in stream:
for choice in chunk.choices:
if choice.delta.content:
print(choice.delta.content, end="", flush=True)
// npm install @pinecone-database/pinecone
import { Pinecone } from '@pinecone-database/pinecone';
// Reads PINECONE_API_KEY from the environment
const pc = new Pinecone();
const assistant = pc.assistant({ name: 'example-assistant' });
const response = await assistant.chatCompletion({
messages: [{ role: 'user', content: 'What is the maximum height of a red pine?' }],
});
console.log(response.choices?.[0]?.message?.content);
// npm install @pinecone-database/pinecone
import { Pinecone } from '@pinecone-database/pinecone';
// Reads PINECONE_API_KEY from the environment
const pc = new Pinecone();
const assistant = pc.assistant({ name: 'example-assistant' });
const stream = await assistant.chatCompletionStream({
messages: [{ role: 'user', content: 'What is the maximum height of a red pine?' }],
});
for await (const chunk of stream) {
for (const choice of chunk.choices) {
if (choice.delta.content) {
process.stdout.write(choice.delta.content);
}
}
}
PINECONE_API_KEY="YOUR_API_KEY"
ASSISTANT_NAME="example-assistant"
curl "https://prod-1-data.ke.pinecone.io/assistant/chat/$ASSISTANT_NAME/chat/completions" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{
"role": "user",
"content": "What is the maximum height of a red pine?"
}
]
}'
PINECONE_API_KEY="YOUR_API_KEY"
ASSISTANT_NAME="example-assistant"
curl "https://prod-1-data.ke.pinecone.io/assistant/chat/$ASSISTANT_NAME/chat/completions" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Pinecone-Api-Version: 2026-07" \
-d '{
"messages": [
{
"role": "user",
"content": "What is the maximum height of a red pine?"
}
],
"stream": true
}'
{
"id": "<string>",
"choices": [
{
"finish_reason": "<string>",
"index": 123,
"message": {
"role": "<string>",
"content": "<string>"
}
}
],
"model": "<string>",
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"code": "INVALID_ARGUMENT",
"message": "Uploaded file can only currently be either a pdf or txt file"
},
"status": 400
}{
"error": {
"code": "UNAUTHENTICATED",
"message": "Invalid API key."
},
"status": 401
}{
"error": {
"code": "NOT_FOUND",
"message": "Assistant \"example-assistant\" not found."
},
"status": 404
}{
"error": {
"code": "UNKNOWN",
"message": "Internal server error"
},
"status": 500
}# pip install --upgrade pinecone
import os
from pinecone import Pinecone
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
response = pc.assistants.chat_completions(
assistant_name="example-assistant",
messages=[{"role": "user", "content": "What is the maximum height of a red pine?"}],
)
print(response.choices[0].message.content)
# pip install --upgrade pinecone
import os
from pinecone import Pinecone
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
stream = pc.assistants.chat_completions(
assistant_name="example-assistant",
messages=[{"role": "user", "content": "What is the maximum height of a red pine?"}],
stream=True,
)
for chunk in stream:
for choice in chunk.choices:
if choice.delta.content:
print(choice.delta.content, end="", flush=True)
// npm install @pinecone-database/pinecone
import { Pinecone } from '@pinecone-database/pinecone';
// Reads PINECONE_API_KEY from the environment
const pc = new Pinecone();
const assistant = pc.assistant({ name: 'example-assistant' });
const response = await assistant.chatCompletion({
messages: [{ role: 'user', content: 'What is the maximum height of a red pine?' }],
});
console.log(response.choices?.[0]?.message?.content);
// npm install @pinecone-database/pinecone
import { Pinecone } from '@pinecone-database/pinecone';
// Reads PINECONE_API_KEY from the environment
const pc = new Pinecone();
const assistant = pc.assistant({ name: 'example-assistant' });
const stream = await assistant.chatCompletionStream({
messages: [{ role: 'user', content: 'What is the maximum height of a red pine?' }],
});
for await (const chunk of stream) {
for (const choice of chunk.choices) {
if (choice.delta.content) {
process.stdout.write(choice.delta.content);
}
}
}
PINECONE_API_KEY="YOUR_API_KEY"
ASSISTANT_NAME="example-assistant"
curl "https://prod-1-data.ke.pinecone.io/assistant/chat/$ASSISTANT_NAME/chat/completions" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{
"role": "user",
"content": "What is the maximum height of a red pine?"
}
]
}'
PINECONE_API_KEY="YOUR_API_KEY"
ASSISTANT_NAME="example-assistant"
curl "https://prod-1-data.ke.pinecone.io/assistant/chat/$ASSISTANT_NAME/chat/completions" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Pinecone-Api-Version: 2026-07" \
-d '{
"messages": [
{
"role": "user",
"content": "What is the maximum height of a red pine?"
}
],
"stream": true
}'
Authorizations
Pinecone API Key
Headers
Required date-based version header
Path Parameters
The name of the assistant to be described.
Body
application/json
The desired configuration to chat with an assistant through an OpenAI-compatible interface.
Represents a request to chat with an assistant.
The list of messages sent to the assistant, used for context retrieval and generating response with the LLM.
Show child attributes
Show child attributes
If false, the assistant returns a single JSON response. If true, the assistant returns a stream of responses.
The large language model used to generate responses.
Controls the randomness of the model's output: lower values make responses more deterministic, while higher values increase creativity and variability. If the model does not support a temperature parameter, the parameter will be ignored.
Optional metadata-based filter to restrict which documents are retrieved for the assistant's response context.
Example:
{ "genre": { "$ne": "documentary" } }
Response
Search request successful.
Describes the response format of a chat request.
A unique identifier for this chat response.
A list of chat completion choices.
Show child attributes
Show child attributes
The name or identifier of the model used to generate this chat response.
Describes the token usage associated with interactions with an assistant.
Show child attributes
Show child attributes
Was this page helpful?