Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Agentic Reasoning on Your Multimodal Data
Activeloop-L0 is a compound AI system that ingests and answers questions from your unstructured, multimodal data. It delivers accurate, traceable answers with clear source citations, ensuring trust and transparency through visual reasoning.
All thanks to Deep Lake, Activeloop provides unique advantages over traditional RAG systems, enabling deeper understanding and control of your data.
💡 Native Multimodal Understanding: Leverage advanced Visual Language Models (VLMs) to intrinsically understand PDFs, PowerPoints, images, audio, and more without brittle OCR or complex pre-processing.
☁️ Your Data, Your Cloud, Your Control: Deploy entirely within your secure cloud infrastructure. Connect private data sources and bring your own models (BYOM), ensuring sensitive data never leaves your perimeter.
✅ Trustworthy & Explainable Results: Deliver highly accurate, grounded answers backed by clear citations directly to the source data, ensuring reliability, auditability, and user trust.
🚀 Accelerate & Automate Workflows: Seamlessly embed deep knowledge retrieval and reasoning into core business processes like compliance checks, research synthesis, and customer support.
🧑💻 Free Your AI Team to Innovate: Eliminate the infrastructure bottleneck. We automate parsing, chunking, embedding, and indexing, letting your team focus on high-value AI applications, not data plumbing.
✨ Unlock Actionable Insights: Discover hidden connections and analyze trends across disparate data types. Extract meaningful insights previously buried in your complex multimodal data assets.
Financial Services: Analyze quarterly reports alongside market news videos and earnings call audio.
Pharma & Life Sciences: Accelerate R&D by connecting research papers, clinical trial data, and lab notes.
Technology: Gain holistic customer understanding by correlating support tickets, call audio, and user session recordings.
Legal & Compliance: Perform deep analysis across case law, contracts, and internal communications with full audit trails.
Basic RAG struggles where enterprise needs are greatest:
Agentic Scaffold: predefined loops and rigid agent scaffolds.
Multimodal Data: Difficulty processing and relating information beyond plain text.
Infrastructure Burden: High cost and effort to build/maintain complex pipelines.
Integration Challenge: Difficulty embedding insights into meaningful workflows.
Ready to unlock the true potential of your enterprise data?
: Dive deeper into concepts, architecture, and API references.
: Set up a basic instance and index your first multimodal data.
: Discuss your specific use case and see a tailored demonstration.
Insurance: Streamline claims processing and enhance fraud detection by correlating claim forms, incident reports, damage photos/videos, repair estimates, and policyholder data.
Control & Security: Concerns over data leaving secure perimeters with SaaS RAG.
High complexity, manual mgmt.
✅ Automated, streamlined
Deployment/Security
Often SaaS, limited control
✅ Your Cloud, Secure Private, BYOM
Accuracy/Explainability
Variable, opaque sourcing
✅ High accuracy with clear citations
Feature
Traditional RAG
Activeloop Knowledge Agents
Data Support
Mostly text-only
✅ Native Multimodal
Reasoning
Limited keyword/semantic search
✅ Advanced relationship & multi-step
Integration
Basic retrieval
✅ Deep workflow integration
Data Pre-processing
Manual/Complex (OCR often)
✅ Automated / Native understanding
Infrastructure
Upload a document and run a query. All within minutes.
Get Token
Sign up at . Navigate to ⚙️ → API tokens, and create a token. Set the token as ACTIVELOOP_TOKEN environment variable.
Upload Documents
We will fetch 4 reference guides from NASA each more than 90 pages and ask a highly complex question.
You can learn about the state by .
Query Data
Once the data is indexed, you can run a query against it as if you are calling your LLM .
import os, io, requests
pdf_urls = ["https://www.nasa.gov/wp-content/uploads/2022/03/sls-reference-guide-2022-v2-508-0.pdf",
"https://www.nasa.gov/wp-content/uploads/2023/02/orion-reference-guide-111022.pdf",
"https://www.lpi.usra.edu/lunar/artemis/Artemis-I-Reference-Guide_NP-2022-03-3045-HQ.pdf",
"https://www.ulalaunch.com/docs/default-source/rockets/2023_vulcan_user_guide.pdf"]
files = [('file', (os.path.basename(url), io.BytesIO(requests.get(url).content))) for url in pdf_urls]
response = requests.post(
'https://api.activeloop.ai/files',
headers={"Authorization": f"Bearer {os.getenv('ACTIVELOOP_TOKEN')}"},
files=files
)
# Onced uploaded, it would take few minutes to indexfrom openai import OpenAI
client = OpenAI(
base_url="https://api.activeloop.ai/",
api_key=os.getenv('ACTIVELOOP_TOKEN')
)
response = client.chat.completions.create(
model="activeloop-l0",
messages=[
{
"role": "user",
"content": "Using the side-view diagrams that annotate overall height, rank SLS Block 1, Orion (CM + SM), " +
"Falcon 9 (v1.2 FT), and Vulcan Centaur by height; which vehicle is the second tallest, " +
"and what is its annotated height (m, one decimal place)?"
}
],
stream=True
)
chunks = [chunk.choices[0] for chunk in response]
thinking = "".join([c.delta.reasoning_content for c in chunks if c.delta.reasoning_content is not None])
answer = "".join([c.delta.content for c in chunks if c.delta.content is not None])
citations = chunks[-1].metadata['relevant_docs']
You can upload the following document types
Supported Document Extensions
PDF Documents
✅
.txt, .md, .json
Text, Markdown and Dictionaries
✅
.docx, .pptx
Microsoft Office
✅
.csv, .xlsx
Table formats
soon
.jpeg, .png
Image formats
✅
.wav, .mp3
Audio formats
✅
.mp4, .mkv, .avi
Video formats
soon
This guide covers how to upload multiple documents to Activeloop and interact with your data through the Chat Completions API.
This section handles batch uploading PDF files from philosophy and mathematics categories providing extra metadata.
import os
import json
import requests
url = 'https://api.activeloop.ai/files'
headers = {'Authorization': f'Bearer {os.getenv("ACTIVELOOP_TOKEN")}'}
for category in ['philosophy', 'mathematics']:
for author in os.listdir(category):
files = [('file', (pdf, open(f'{category}/{author}/{pdf}', 'rb'))) for pdf in os.listdir(f'{category}/{author}')]
# specify any extra metadata
metadata = {
'category': category,
'author': author
}
data = {'metadata': json.dumps(metadata)}
# upload files
response = requests.post(url, headers=headers, files=files, data=data)
print(response.status_code)You can learn more on supported document type by going over modalities.
Hybrid visual search. Just returns top_k elements.
activeloop-l0
~40s
Reasoning iterations with evidence collection and verification including inline citations.
1M input tokens is roughly 1,000 pages of a document. Output tokens include thinking and search results.
activeloop-l0
$1.00 / 1M tokens
$15.00 / 1M token
$99 / 100GB month
Financial: 2,100 pages of documents including quarterly reports, market news video transcripts, and earnings call transcripts.
Approximate total cost is $122/month | Input 2M tokens → $2, Output 8M tokens → $120, Free Storage
Healthcare: 8,000 pages of research documents including research papers, clinical trial documents, lab notes, and supplementary data.
Approximate total cost is $707/month | Input 8M tokens → $8, Output 40M tokens → $600, Storage Tier 100GB -> $99
Insurance: 120,000 pages of insurance documents including claim forms, incident reports, damage photos/videos, repair estimates, policyholder data, and investigation reports.
Approximate total cost is $2,568/month | Input 120M tokens → $120, Output 150M tokens → $2,250, Storage Tier 200GB → $198
Activeloop is trusted by F500 including likes of Bayer, Flagship Pioneering, and Matterport.
Deploy on your cloud, ensuring data never leaves your infrastructure.
Integrate custom storage and LLMs.
Enjoy SOC2 compliance, fine-grained access control, and SSO.
Book a call to discuss enterprise deployment.
activeloop-l0-retrieval
1-5s
activeloop-l0-retrieval is used there is no reasoning or summary returned. Only top_k results.Now, we can filter files based on metadata, before running the query.
You can learn more about on various ways you can filter the data via Query Syntax.
import os, requests
url = "https://api.activeloop.ai/chat/completions"
token = os.environ["ACTIVELOOP_TOKEN"]
headers = {'Authorization': f'Bearer {token}'}
payload = {
"model": "activeloop-l0",
"messages": [
{
"role": "user",
"content": "What is logic?",
}
]
}
response = requests.post(url, headers=headers, json=payload)
# Print the response
print(response.json())payload = {
"model": "activeloop-l0-retrieval",
"messages": [
{
"role": "user",
"content": [
{
"type": "filter",
"top_k": 3
},
{
"type": "text",
"text": "What is logic?" # query
}
]
}
]
}
response = requests.post(url, headers=headers, json=payload)
print(response.json()["choices"]) # top k elementspayload = {
"model": "activeloop-l0",
"messages": [
{
"role": "user",
"content": [
{
"type": "filter",
"filter": "metadata.author == 'hegel'"
},
{
"type": "text",
"text": "What is logic?"
}
]
}
],
}
response = requests.post(url, headers=headers, json=payload)
print(response.json())payload = {
"model": "activeloop-l0",
"messages": [
{
"role": "user",
"content": [
{
"type": "filter",
"filter": "metadata.author != 'hegel'"
},
{
"type": "text",
"text": "What is logic?"
}
]
}
],
}
response = requests.post(url, headers=headers, json=payload)
print(response.json())Cheatsheet for filtering the data
A filter expression consists of one or more conditions that can be combined using logical operators. Each condition typically follows this pattern:
The syntax supports the following data types:
Strings: Enclosed in double quotes ("value") or single quotes ('value')
Numbers: Integers or decimals (42, 3.14)
Booleans: true
Conditions can be combined using logical operators:
AND: condition1 and condition2
OR: condition1 or condition2
Parentheses can be used to group conditions and control precedence:
For nested data structures, use dot notation to access properties:
The following keywords are reserved and should not be used as field names:
and
or
in
like
Use parentheses to make complex expressions clearer
Be consistent with string quotes (prefer double quotes)
Use whitespace to improve readability
For complex filters, break expressions into multiple lines
column operator valueLess than
quantity < 5
<=
Less than or equal to
temperature <= 32
in
Value is in a list
status in ["active", "pending"]
like
Pattern matching
name like "%Smith%"
is null
Value is null
address is null
is not null
Value is not null
email is not null
falseLists: Enclosed in square brackets, with comma-separated values ([1, 2, 3], ["active", "pending"])
is
null
not
true
false
=, ==
Equals
name = "John"
!=, <>
Not equals
status != "inactive"
>
Greater than
age > 30
>=
Greater than or equal to
price >= 100
<
Following the tutorial on QuickStart, instead of waiting the whole reasoning to be completed, you can stream intermediate tokens.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.activeloop.ai/",
api_key=os.getenv('ACTIVELOOP_TOKEN')
)
stream = client.chat.completions.create(
model="activeloop-l0",
messages=[{"role": "user", "content": "what is the AIME score of DeepSeek R1?"}],
stream=True,
)
for event in stream:
print(event)(age > 30 and status = "active") or role = "admin"user.profile.name = "John"
metadata.tags[0] = "important"// Simple equality check
name = "John"
// Numeric comparison
age > 30
// Boolean value
is_active = true// Using AND
age > 30 and status = "active"
// Using OR
status = "pending" or status = "in_review"
// Combining with parentheses
(age > 30 and status = "active") or role = "admin"// Check if value is in a list
status in ["active", "pending", "in_review"]
// Empty list
tags in []// Names that contain "Smith"
name like "%Smith%"
// Email addresses from a specific domain
email like "%@example.com"
// Starts with a specific prefix
product_code like "ABC%"// Check if a field is null
address is null
// Check if a field is not null
email is not null// Access nested object properties
user.profile.address = "New York"
// Access array elements
metadata.tags[0] = "important"
// Deep nesting
order.items[0].product.name = "Widget"// Complex filter combining multiple conditions
(status in ["active", "pending"] and created_date > "2023-01-01") or
(is_priority = true and (assigned_to = "John" or assigned_to is null))
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
^[a-z0-9]+(?:[-_][a-z0-9]+)*$Successful Response
Validation Error
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the workspace to get.
Successful Response
Validation Error
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the workspace to delete.
Successful Response
Validation Error
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the workspace to add user to.
Successful Response
Validation Error
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the workspace to update user info.
Successful Response
Validation Error
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the workspace to remove user from.
The ID of the user.
Successful Response
Validation Error
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the workspace to list users from.
Successful Response
Validation Error
Upload a file with optional metadata.
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
user_dataPossible values: JSON string with file metadata
Instructions used to process the file
defaultSuccessful Response
Validation Error
Returns a list of files, filtered by the organization.
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
List files in workspace
defaultCursor for pagination
Limit the number of returned files
10000Sort order by creation timestamp
descFilter by purpose
Filter by metadata
Successful Response
Validation Error
Returns information about a specific file, verifying organization access.
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the file
Get file from workspace
defaultSuccessful Response
Validation Error
Delete a file, verifying organization access.
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the file
Delete file from workspace
defaultSuccessful Response
Validation Error
Returns the contents of the specified file, verifying organization access.
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the file
The workspace id to get file content from
defaultSuccessful Response
Validation Error
Update metadata for a specific file, verifying organization access.
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the file
The workspace id to update th file in
defaultThe metadata to update. instructions key is considered as an instruction to update metadata by AI.
Successful Response
Validation Error
Create a chat completion with OpenAI-compatible format
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
defaultactiveloop-l0111false00falsefalseGet messages for a chat completion
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the chat completion
The ID of workspace to lookup chat completion messages in
defaultIdentifier for the last message from the previous pagination request
Number of messages to retrieve
20Sort order for messages by timestamp
ascList stored Chat Completions
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of workspace to lookup chat completions in
defaultIdentifier for the last chat completion from the previous pagination request
Number of Chat Completions to retrieve
20Sort order for Chat Completions by timestamp
ascPossible values: Filter by model
Successful Response
Validation Error
Get a stored chat completion
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the chat completion to retrieve
The ID of workspace to lookup chat completion in
defaultSuccessful Response
Validation Error
Update metadata for a chat completion
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the chat completion to update
The ID of workspace to update chat completion in
defaultSuccessful Response
Validation Error
Get messages for a chat completion
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the chat completion
The ID of workspace to lookup chat completion messages in
defaultIdentifier for the last message from the previous pagination request
Number of messages to retrieve
20Sort order for messages by timestamp
ascSuccessful Response
Validation Error
Delete a chat completion
Enter your bearer token in the format 'your-token' (without quotes or 'Bearer' prefix)
The ID of the chat completion to delete
The ID of workspace to delete chat completion in
defaultSuccessful Response
Validation Error
No content
No content
No content
No content
No content
No content
{
"data": [
{
"id": "text",
"name": "text",
"creator_user_id": "text",
"org_id": "text",
"created_at": "2025-12-13T14:02:36.540Z"
}
]
}{
"id": "text",
"name": "text",
"creator_user_id": "text",
"org_id": "text",
"created_at": "2025-12-13T14:02:36.540Z"
}{
"data": [
{
"user_id": "text",
"access": "writer",
"created_at": "2025-12-13T14:02:36.540Z"
}
]
}POST /workspaces HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 27
{
"id": "text",
"name": "text"
}GET /workspaces HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
GET /workspaces/{workspace_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
DELETE /workspaces/{workspace_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
POST /workspaces/{workspace_id}/user HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 33
{
"user": "text",
"access": "writer"
}PUT /workspaces/{workspace_id}/user HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 33
{
"user": "text",
"access": "writer"
}DELETE /workspaces/{workspace_id}/user/{user_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
GET /workspaces/{workspace_id}/users HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
[
{
"id": "text",
"object": "file",
"bytes": 1,
"created_at": 1,
"filename": "text",
"purpose": "user_data",
"status": "uploaded",
"status_details": "text",
"expires_at": 1,
"org_id": "text",
"workspace_id": "default",
"user_id": "text",
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
]{
"data": [
{
"id": "text",
"object": "file",
"bytes": 1,
"created_at": 1,
"filename": "text",
"purpose": "user_data",
"status": "uploaded",
"status_details": "text",
"expires_at": 1,
"org_id": "text",
"workspace_id": "default",
"user_id": "text",
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
],
"object": "list",
"total": 1
}{
"id": "text",
"object": "file",
"bytes": 1,
"created_at": 1,
"filename": "text",
"purpose": "user_data",
"status": "uploaded",
"status_details": "text",
"expires_at": 1,
"org_id": "text",
"workspace_id": "default",
"user_id": "text",
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}{
"id": "text",
"object": "file",
"deleted": true
}PATCH /files/{file_id}/metadata HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 38
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}{
"id": "text",
"object": "file",
"bytes": 1,
"created_at": 1,
"filename": "text",
"purpose": "user_data",
"status": "uploaded",
"status_details": "text",
"expires_at": 1,
"org_id": "text",
"workspace_id": "default",
"user_id": "text",
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}POST /files HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 103
{
"file": [
"binary"
],
"purpose": "user_data",
"metadata": "text",
"instructions": "text",
"workspace": "default"
}GET /files/{file_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
DELETE /files/{file_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
GET /files/{file_id}/content HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
GET /files HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
Successful Response
Validation Error
No content
Successful Response
Validation Error
POST /chat/completions HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 566
{
"workspace": "default",
"model": "activeloop-l0",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "text"
}
]
}
],
"temperature": 1,
"top_p": 1,
"n": 1,
"stream": false,
"max_tokens": 1,
"max_completion_tokens": 1,
"presence_penalty": 0,
"frequency_penalty": 0,
"logit_bias": {
"ANY_ADDITIONAL_PROPERTY": 1
},
"logprobs": false,
"top_logprobs": 1,
"stop": "text",
"seed": 1,
"response_format": {
"type": "text"
},
"user": "text",
"stream_options": {
"include_usage": true
},
"store": false,
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "text"
},
"modalities": [
"text"
],
"service_tier": "text",
"reasoning_effort": "low"
}GET /chat/completions/{completion_id}/messages HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
{
"object": "list",
"data": [
{
"id": "text",
"object": "chat.completion",
"created": 1,
"model": "text",
"system_fingerprint": "text",
"choices": [
{
"index": 1,
"message": {
"role": "system",
"content": "text",
"reasoning_content": "text",
"refusal": null,
"annotations": [
{
"type": "text",
"text": "text",
"start_index": 1,
"end_index": 1,
"file_citation": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"file_path": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
]
},
"finish_reason": "text",
"logprobs": {
"content": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
]
},
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
],
"usage": {
"prompt_tokens": 1,
"completion_tokens": 1,
"total_tokens": 1
},
"perception_usage": {
"prompt_tokens": 1,
"completion_tokens": 1,
"total_tokens": 1
},
"service_tier": "text",
"request_id": "text",
"seed": 1,
"top_p": 1,
"temperature": 1,
"presence_penalty": 1,
"frequency_penalty": 1,
"input_user": "text",
"tools": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
],
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"response_format": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"responses": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
],
"first_id": "text",
"last_id": "text",
"has_more": false
}{
"id": "text",
"object": "chat.completion",
"created": 1,
"model": "text",
"system_fingerprint": "text",
"choices": [
{
"index": 1,
"message": {
"role": "system",
"content": "text",
"reasoning_content": "text",
"refusal": null,
"annotations": [
{
"type": "text",
"text": "text",
"start_index": 1,
"end_index": 1,
"file_citation": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"file_path": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
]
},
"finish_reason": "text",
"logprobs": {
"content": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
]
},
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
],
"usage": {
"prompt_tokens": 1,
"completion_tokens": 1,
"total_tokens": 1
},
"perception_usage": {
"prompt_tokens": 1,
"completion_tokens": 1,
"total_tokens": 1
},
"service_tier": "text",
"request_id": "text",
"seed": 1,
"top_p": 1,
"temperature": 1,
"presence_penalty": 1,
"frequency_penalty": 1,
"input_user": "text",
"tools": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
],
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"response_format": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"responses": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}{
"id": "text",
"object": "chat.completion",
"created": 1,
"model": "text",
"system_fingerprint": "text",
"choices": [
{
"index": 1,
"message": {
"role": "system",
"content": "text",
"reasoning_content": "text",
"refusal": null,
"annotations": [
{
"type": "text",
"text": "text",
"start_index": 1,
"end_index": 1,
"file_citation": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"file_path": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
]
},
"finish_reason": "text",
"logprobs": {
"content": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
]
},
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}
],
"usage": {
"prompt_tokens": 1,
"completion_tokens": 1,
"total_tokens": 1
},
"perception_usage": {
"prompt_tokens": 1,
"completion_tokens": 1,
"total_tokens": 1
},
"service_tier": "text",
"request_id": "text",
"seed": 1,
"top_p": 1,
"temperature": 1,
"presence_penalty": 1,
"frequency_penalty": 1,
"input_user": "text",
"tools": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
],
"metadata": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"response_format": {
"ANY_ADDITIONAL_PROPERTY": "anything"
},
"responses": {
"ANY_ADDITIONAL_PROPERTY": "anything"
}
}{
"object": "list",
"data": [
{
"id": "text",
"role": "system",
"content": "text",
"name": "text",
"content_parts": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
]
}
],
"first_id": "text",
"last_id": "text",
"has_more": false
}{
"id": "text",
"object": "chat.completion.deleted",
"deleted": true
}GET /chat/completions/{completion_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
GET /chat/completions/{completion_id}/messages HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
DELETE /chat/completions/{completion_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
GET /chat/completions HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*
POST /chat/completions/{completion_id} HTTP/1.1
Host: api.activeloop.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 34
{
"ANY_ADDITIONAL_PROPERTY": "text"
}{
"object": "list",
"data": [
{
"id": "text",
"role": "system",
"content": "text",
"name": "text",
"content_parts": [
{
"ANY_ADDITIONAL_PROPERTY": "anything"
}
]
}
],
"first_id": "text",
"last_id": "text",
"has_more": false
}