GET
/
session
/
{session_id}
import honeyhive

s = honeyhive.HoneyHive(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
)


res = s.session.get_session(session_id='<value>')

if res.event is not None:
    # handle response
    pass
{
  "project_id": "New Project",
  "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"
  }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
session_id
string
required

Response

200 - application/json
Session details
​
project_id
string

Name of project associated with the event

​
source
string

Source of the event - production, staging, etc

​
event_name
string

Name of the event

​
event_type
enum<string>

Specify whether the event is of "session", "model", "tool" or "chain" type

Available options:
session,
model,
tool,
chain
​
event_id
string

Unique id of the event, if not set, it will be auto-generated

​
session_id
string

Unique id of the session associated with the event, if not set, it will be auto-generated

​
parent_id
string

Id of the parent event if nested

​
children_ids
string[]

Id of events that are nested within the event

​
config
object

Associated configuration JSON for the event - model name, vector index name, etc

​
inputs
object

Input JSON given to the event - prompt, chunks, etc

​
outputs
object

Final output JSON of the event

​
error
string

Any error description if event failed

​
start_time
number

UTC timestamp (in milliseconds) for the event start

​
end_time
integer

UTC timestamp (in milliseconds) for the event end

​
duration
number

How long the event took in milliseconds

​
metadata
object

Any system or application metadata associated with the event

​
feedback
object

Any user feedback provided for the event output

​
metrics
object

Any values computed over the output of the event

​
user_properties
object

Any user properties associated with the event

Was this page helpful?

Suggest editsRaise issue