For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Sign inBook a demo
DocsReferenceChangelog
DocsReferenceChangelog
  • Introduction
    • SDKs
    • Errors
  • Humanloop API
      • STREAMChat
      • STREAMChat Deployed
      • STREAMChat Model Config
      • STREAMCreate Experiment Stream
LogoLogo
Sign inBook a demo
Humanloop APIChats

Create Experiment

POST
https://api.humanloop.com/v4/chat-experiment
POST
/v4/chat-experiment
$curl -X POST https://api.humanloop.com/v4/chat-experiment
200Successful
1{
2  "data": [
3    {
4      "id": "id",
5      "index": 1,
6      "output": "output",
7      "raw_output": "raw_output",
8      "model_config_id": "model_config_id",
9      "output_message": {
10        "role": "user"
11      },
12      "inputs": {
13        "key": "value"
14      },
15      "finish_reason": "finish_reason",
16      "tool_results": [
17        {
18          "id": "id",
19          "name": "name",
20          "signature": "signature",
21          "result": "result"
22        }
23      ],
24      "messages": [
25        {
26          "role": "user"
27        }
28      ],
29      "tool_calls": [
30        {
31          "id": "id",
32          "type": "function",
33          "function": {
34            "name": "name"
35          }
36        }
37      ],
38      "tool_call": {
39        "name": "name"
40      }
41    }
42  ],
43  "provider_responses": [
44    {
45      "key": "value"
46    }
47  ],
48  "project_id": "project_id",
49  "num_samples": 1,
50  "logprobs": 1,
51  "suffix": "suffix",
52  "user": "user",
53  "usage": {
54    "prompt_tokens": 1,
55    "generation_tokens": 1,
56    "total_tokens": 1,
57    "reasoning_tokens": 1
58  },
59  "metadata": {
60    "key": "value"
61  },
62  "provider_request": {
63    "key": "value"
64  },
65  "session_id": "session_id",
66  "tool_choice": "none"
67}
Was this page helpful?
Previous

Create Experiment Stream

Next
Built with

Response

datalist of objects
Array containing the chat responses.
provider_responseslist of any
The raw responses returned by the model provider.
project_idstring
Unique identifier of the parent project. Will not be provided if the request was made without providing a project name or id
num_samplesintegerDefaults to 1
The number of chat responses.
logprobsinteger

Include the log probabilities of the top n tokens in the provider_response

suffixstring
The suffix that comes after a completion of inserted text. Useful for completions that act like inserts.
userstring

End-user ID passed through to provider call.

usageobject
Counts of the number of tokens used and related stats.
metadatamap from strings to any
Any additional metadata to record.
provider_requestmap from strings to any
The raw request sent to the model provider.
session_idstring
ID of the session if it belongs to one.
tool_choice"none" or "auto" or "required" or object

Controls how the model uses tools. The following options are supported: ‘none’ forces the model to not call a tool; the default when no tools are provided as part of the model config. ‘auto’ the model can decide to call one of the provided tools; the default when tools are provided as part of the model config. Providing {‘type’: ‘function’, ‘function’: {name’: <TOOL_NAME>}} forces the model to use the named function.