- Knowledge
- Community
- GETRetrieve a list of configurations
- POSTCreate a new configuration
- PUTUpdate an existing configuration
- DELDelete a configuration
- GETRetrieve a list of datapoints
- PUTUpdate a specific datapoint
- POSTCreate a new datapoint
- GETRetrieve a specific datapoint
- DELDelete a specific datapoint
Configurations
Datapoints
Process an event trace for a given session
curl --request POST \
--url https://api.honeyhive.ai/session/{session_id}/traces \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"logs": [
{
"project_id": "65e0fc2d6a2eb95f55a92cbc",
"source": "playground",
"session_id": "caf77ace-3417-4da4-944d-f4a0688f3c23",
"event_id": "7f22137a-6911-4ed3-bc36-110f1dde6b66",
"parent_id": "caf77ace-3417-4da4-944d-f4a0688f3c23",
"event_type": "model",
"event_name": "Model Completion",
"config": {
"model": "gpt-3.5-turbo",
"version": "v0.1 - Fork",
"provider": "openai",
"hyperparameters": {
"temperature": 0,
"top_p": 1,
"max_tokens": 1000,
"presence_penalty": 0,
"frequency_penalty": 0,
"stop": [],
"n": 1
},
"template": [
{
"role": "system",
"content": "Answer the user'\''s question only using provided context.\n\nContext: {{ context }}"
},
{
"role": "user",
"content": "{{question}}"
}
],
"type": "chat"
},
"children_ids": [],
"inputs": {
"context": "Hello world",
"question": "What is in the context?",
"chat_history": [
{
"role": "system",
"content": "Answer the user'\''s question only using provided context.\n\nContext: Hello world"
},
{
"role": "user",
"content": "What is in the context?"
}
]
},
"outputs": {
"role": "assistant",
"content": "Hello world"
},
"error": null,
"start_time": "2024-04-01 22:38:19",
"end_time": "2024-04-01 22:38:19",
"duration": 824.8056,
"metadata": {
"cost": 0.00008,
"completion_tokens": 23,
"prompt_tokens": 35,
"total_tokens": 58
},
"feedback": {},
"metrics": {
"Answer Faithfulness": 5,
"Answer Faithfulness_explanation": "The AI assistant'\''s answer is a concise and accurate description of Ramp'\''s API. It provides a clear explanation of what the API does and how developers can use it to integrate Ramp'\''s financial services into their own applications. The answer is faithful to the provided context.",
"Number of words": 18
},
"user_properties": {
"user": "google-oauth2|111840237613341303366"
}
}
]
}'
{
"result": "<string>"
}
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Path Parameters
The ID of the session to which this event trace belongs
Body
Please refer to the events POST docs for required fields
UUID of project associated with the event
Source of the event - production, staging, etc
Name of the event
Specify whether the event is of "model", "tool" or "chain" type
model
, tool
, chain
Unique id of the event, if not set, it will be auto-generated
Unique id of the session associated with the event, if not set, it will be auto-generated
Id of the parent event if nested
Id of events that are nested within the event
Associated configuration JSON for the event - model name, vector index name, etc
Input JSON given to the event - prompt, chunks, etc
Messages passed to the model
Final output JSON of the event
Any error description if event failed
UTC timestamp (in milliseconds) for the event start
UTC timestamp (in milliseconds) for the event end
How long the event took in milliseconds
Any system or application metadata associated with the event
Any user feedback provided for the event output
Any values computed over the output of the event
Any user properties associated with the event
Response
curl --request POST \
--url https://api.honeyhive.ai/session/{session_id}/traces \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"logs": [
{
"project_id": "65e0fc2d6a2eb95f55a92cbc",
"source": "playground",
"session_id": "caf77ace-3417-4da4-944d-f4a0688f3c23",
"event_id": "7f22137a-6911-4ed3-bc36-110f1dde6b66",
"parent_id": "caf77ace-3417-4da4-944d-f4a0688f3c23",
"event_type": "model",
"event_name": "Model Completion",
"config": {
"model": "gpt-3.5-turbo",
"version": "v0.1 - Fork",
"provider": "openai",
"hyperparameters": {
"temperature": 0,
"top_p": 1,
"max_tokens": 1000,
"presence_penalty": 0,
"frequency_penalty": 0,
"stop": [],
"n": 1
},
"template": [
{
"role": "system",
"content": "Answer the user'\''s question only using provided context.\n\nContext: {{ context }}"
},
{
"role": "user",
"content": "{{question}}"
}
],
"type": "chat"
},
"children_ids": [],
"inputs": {
"context": "Hello world",
"question": "What is in the context?",
"chat_history": [
{
"role": "system",
"content": "Answer the user'\''s question only using provided context.\n\nContext: Hello world"
},
{
"role": "user",
"content": "What is in the context?"
}
]
},
"outputs": {
"role": "assistant",
"content": "Hello world"
},
"error": null,
"start_time": "2024-04-01 22:38:19",
"end_time": "2024-04-01 22:38:19",
"duration": 824.8056,
"metadata": {
"cost": 0.00008,
"completion_tokens": 23,
"prompt_tokens": 35,
"total_tokens": 58
},
"feedback": {},
"metrics": {
"Answer Faithfulness": 5,
"Answer Faithfulness_explanation": "The AI assistant'\''s answer is a concise and accurate description of Ramp'\''s API. It provides a clear explanation of what the API does and how developers can use it to integrate Ramp'\''s financial services into their own applications. The answer is faithful to the provided context.",
"Number of words": 18
},
"user_properties": {
"user": "google-oauth2|111840237613341303366"
}
}
]
}'
{
"result": "<string>"
}