Video Q&A

The Vision API provides powerful question-answering capabilities for your videos. Once a video has been indexed, you can ask natural language questions about its content and receive AI-powered answers.

The Video Q&A API is designed for videos longer than 30 seconds. It indexes your video for efficient retrieval and analysis across longer content.

For videos 30 seconds or shorter, use the Chat API with multimodal inputs instead — it accepts video directly in the conversation without requiring a separate indexing step.

Prerequisites

Before using Video Q&A, ensure your video has been successfully indexed:

Upload a video with index=true
Check indexing status - it should be "indexed"
Wait for processing if status is "indexing"

Ask Questions

Bash

Use the /v1/qa/chat endpoint to ask questions about your videos:

$ curl -X POST https://vision-agent.api.reka.ai/v1/qa/chat \
>   -H "X-Api-Key: YOUR_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "video_id": "550e8400-e29b-41d4-a716-446655440000",
>     "messages": [
>       {
>         "role": "user",
>         "content": "What is happening in this video?"
>       }
>     ]
>   }'

Python

1 import requests
2 import json
3 
4 url = f"{BASE_URL}/v1/qa/chat"
5 
6 # Chat request body
7 payload = {
8     "video_id": "550e8400-e29b-41d4-a716-446655440000",
9     "messages": [
10       {
11         "role": "user",
12         "content": "What is happening in this video?"
13       }
14     ]
15 }
16 
17 headers = {
18     "X-Api-Key": REKA_API_KEY,
19     "Content-Type": "application/json",
20 }
21 
22 response = requests.post(url, json=payload, headers=headers)
23 print(response.status_code, response.json())

Request Parameters

video_id (optional): ID of the video to analyze
messages (optional): List of chat messages

Using Chat Messages

For multi-turn conversations, use the messages parameter:

Bash

$ curl -X POST https://vision-agent.api.reka.ai/v1/qa/chat \
>   -H "X-Api-Key: YOUR_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "video_id": "550e8400-e29b-41d4-a716-446655440000",
>     "messages": [
>       {
>         "role": "user",
>         "content": "What is happening in this video?"
>       },
>       {
>         "role": "assistant",
>         "content": "The video shows a person walking on the beach during sunset."
>       },
>       {
>         "role": "user",
>         "content": "What is the color of the car in the video?"
>       }
>     ]
>   }'

Python

1 import requests
2 import json
3 
4 url = f"{BASE_URL}/v1/qa/chat"
5 
6 # Chat request body
7 payload = {
8     "video_id": "550e8400-e29b-41d4-a716-446655440000",
9     "messages": [
10       {
11         "role": "user",
12         "content": "What is happening in this video?"
13       },
14       {
15         "role": "assistant",
16         "content": "The video shows a person walking on the beach during sunset."
17       },
18       {
19         "role": "user",
20         "content": "What is the color of the car in the video?"
21       }
22     ]
23 }
24 
25 headers = {
26     "X-Api-Key": REKA_API_KEY,
27     "Content-Type": "application/json",
28 }
29 
30 response = requests.post(url, json=payload, headers=headers)
31 print(response.status_code, response.json())

Streaming Responses

For real-time responses, set stream=true in your request:

Bash

$ curl -X POST https://vision-agent.api.reka.ai/v1/qa/chat \
>   -H "X-Api-Key: YOUR_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "video_id": "550e8400-e29b-41d4-a716-446655440000",
>     "stream": true,
>     "messages": [
>       {
>         "role": "user",
>         "content": "What is happening in this video?"
>       }
>     ]
>   }'

Python

1 import requests
2 import json
3 
4 url = f"{BASE_URL}/v1/qa/chat"
5 
6 payload = {
7     "video_id": "550e8400-e29b-41d4-a716-446655440000",
8     "stream": True,
9     "messages": [
10       {
11         "role": "user",
12         "content": "What is happening in this video?"
13       }
14     ]
15 }
16 
17 headers = {
18     "X-Api-Key": REKA_API_KEY,
19     "Content-Type": "application/json",
20 }
21 
22 response = requests.post(url, json=payload, headers=headers, stream=True)
23 for line in response.iter_lines():
24     if line:
25         print(line.decode('utf-8'))

This returns a Server-Sent Events (SSE) stream with real-time updates.

Response Format

Chat Response

1 {
2   "chat_response": "The video shows a person walking on the beach during sunset.",
3   "status": "success",
4 }

Stream Response

1 {
2   "event": "qa_stream",
3   "data": {
4     "chat_response": "The video shows a person walking on the beach during sunset.",
5     "status": "success",
6   }
7 }

When the stream is complete, a final event is sent:

1 {
2   "event": "done",
3   "data": "[DONE]"
4 }

Question Examples

Here are some example questions you can ask:

General: “What is happening in this video?”
Specific: “What color is the car in the video?”
Temporal: “What happens at the beginning of the video?”
Analytical: “How many people are in the scene?”
Descriptive: “Describe the setting and atmosphere”

Best Practices

Be specific in your questions for better answers
Check indexing status before asking questions
Use streaming for long videos or complex questions

Error Handling

Video not found: Ensure the video_id is correct
Video not indexed: Wait for indexing to complete
Indexing failed: Re-upload the video with index=true

The Video Q&A API is designed for videos longer than 30 seconds. It indexes your video for efficient retrieval and analysis across longer content.

For videos 30 seconds or shorter, use the Chat API with multimodal inputs instead — it accepts video directly in the conversation without requiring a separate indexing step.

Prerequisites

Before using Video Q&A, ensure your video has been successfully indexed:

Upload a video with index=true
Check indexing status - it should be "indexed"
Wait for processing if status is "indexing"

Ask Questions

Bash

Use the /v1/qa/chat endpoint to ask questions about your videos:

$ curl -X POST https://vision-agent.api.reka.ai/v1/qa/chat \
>   -H "X-Api-Key: YOUR_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "video_id": "550e8400-e29b-41d4-a716-446655440000",
>     "messages": [
>       {
>         "role": "user",
>         "content": "What is happening in this video?"
>       }
>     ]
>   }'

Python

1 import requests
2 import json
3 
4 url = f"{BASE_URL}/v1/qa/chat"
5 
6 # Chat request body
7 payload = {
8     "video_id": "550e8400-e29b-41d4-a716-446655440000",
9     "messages": [
10       {
11         "role": "user",
12         "content": "What is happening in this video?"
13       }
14     ]
15 }
16 
17 headers = {
18     "X-Api-Key": REKA_API_KEY,
19     "Content-Type": "application/json",
20 }
21 
22 response = requests.post(url, json=payload, headers=headers)
23 print(response.status_code, response.json())

Request Parameters

video_id (optional): ID of the video to analyze
messages (optional): List of chat messages

Using Chat Messages

For multi-turn conversations, use the messages parameter:

Bash

$ curl -X POST https://vision-agent.api.reka.ai/v1/qa/chat \
>   -H "X-Api-Key: YOUR_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "video_id": "550e8400-e29b-41d4-a716-446655440000",
>     "messages": [
>       {
>         "role": "user",
>         "content": "What is happening in this video?"
>       },
>       {
>         "role": "assistant",
>         "content": "The video shows a person walking on the beach during sunset."
>       },
>       {
>         "role": "user",
>         "content": "What is the color of the car in the video?"
>       }
>     ]
>   }'

Python

1 import requests
2 import json
3 
4 url = f"{BASE_URL}/v1/qa/chat"
5 
6 # Chat request body
7 payload = {
8     "video_id": "550e8400-e29b-41d4-a716-446655440000",
9     "messages": [
10       {
11         "role": "user",
12         "content": "What is happening in this video?"
13       },
14       {
15         "role": "assistant",
16         "content": "The video shows a person walking on the beach during sunset."
17       },
18       {
19         "role": "user",
20         "content": "What is the color of the car in the video?"
21       }
22     ]
23 }
24 
25 headers = {
26     "X-Api-Key": REKA_API_KEY,
27     "Content-Type": "application/json",
28 }
29 
30 response = requests.post(url, json=payload, headers=headers)
31 print(response.status_code, response.json())

Streaming Responses

For real-time responses, set stream=true in your request:

Bash

$ curl -X POST https://vision-agent.api.reka.ai/v1/qa/chat \
>   -H "X-Api-Key: YOUR_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "video_id": "550e8400-e29b-41d4-a716-446655440000",
>     "stream": true,
>     "messages": [
>       {
>         "role": "user",
>         "content": "What is happening in this video?"
>       }
>     ]
>   }'

Python

1 import requests
2 import json
3 
4 url = f"{BASE_URL}/v1/qa/chat"
5 
6 payload = {
7     "video_id": "550e8400-e29b-41d4-a716-446655440000",
8     "stream": True,
9     "messages": [
10       {
11         "role": "user",
12         "content": "What is happening in this video?"
13       }
14     ]
15 }
16 
17 headers = {
18     "X-Api-Key": REKA_API_KEY,
19     "Content-Type": "application/json",
20 }
21 
22 response = requests.post(url, json=payload, headers=headers, stream=True)
23 for line in response.iter_lines():
24     if line:
25         print(line.decode('utf-8'))

This returns a Server-Sent Events (SSE) stream with real-time updates.

Response Format

Chat Response

1 {
2   "chat_response": "The video shows a person walking on the beach during sunset.",
3   "status": "success",
4 }

Stream Response

1 {
2   "event": "qa_stream",
3   "data": {
4     "chat_response": "The video shows a person walking on the beach during sunset.",
5     "status": "success",
6   }
7 }

When the stream is complete, a final event is sent:

1 {
2   "event": "done",
3   "data": "[DONE]"
4 }

Question Examples

Here are some example questions you can ask:

General: “What is happening in this video?”
Specific: “What color is the car in the video?”
Temporal: “What happens at the beginning of the video?”
Analytical: “How many people are in the scene?”
Descriptive: “Describe the setting and atmosphere”

Best Practices

Be specific in your questions for better answers
Check indexing status before asking questions
Use streaming for long videos or complex questions

Error Handling

Video not found: Ensure the video_id is correct
Video not indexed: Wait for indexing to complete
Indexing failed: Re-upload the video with index=true

$	curl -X POST https://vision-agent.api.reka.ai/v1/qa/chat \
>	-H "X-Api-Key: YOUR_API_KEY" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"video_id": "550e8400-e29b-41d4-a716-446655440000",
>	"messages": [
>	{
>	"role": "user",
>	"content": "What is happening in this video?"
>	}
>	]
>	}'

1	import requests
2	import json
3
4	url = f"{BASE_URL}/v1/qa/chat"
5
6	# Chat request body
7	payload = {
8	"video_id": "550e8400-e29b-41d4-a716-446655440000",
9	"messages": [
10	{
11	"role": "user",
12	"content": "What is happening in this video?"
13	}
14	]
15	}
16
17	headers = {
18	"X-Api-Key": REKA_API_KEY,
19	"Content-Type": "application/json",
20	}
21
22	response = requests.post(url, json=payload, headers=headers)
23	print(response.status_code, response.json())

1	{
2	"chat_response": "The video shows a person walking on the beach during sunset.",
3	"status": "success",
4	}

1	{
2	"event": "qa_stream",
3	"data": {
4	"chat_response": "The video shows a person walking on the beach during sunset.",
5	"status": "success",
6	}
7	}