You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This field group definition is based on the Gen AI namespace of the OpenTelemetry Semantic Conventions (https://opentelemetry.io/docs/specs/semconv/attributes-registry/gen-ai/).
9
9
10
10
fields:
11
-
- name: gen_ai.agent.description
12
-
type: text
13
-
description: Free-form description of the GenAI agent provided by the application.
14
-
example: Helps with math problems; Generates fiction stories
15
-
- name: gen_ai.agent.id
16
-
type: keyword
17
-
description: The unique identifier of the GenAI agent.
18
-
example: asst_5j66UpCpwteGg4YSxUnt7lPY
19
-
- name: gen_ai.agent.name
20
-
type: keyword
21
-
description: Human-readable name of the GenAI agent provided by the application.
22
-
example: Math Tutor; Fiction Writer
23
-
- name: gen_ai.operation.name
24
-
type: keyword
25
-
description: The name of the operation being performed.
26
-
example: chat; text_completion; embeddings
27
-
- name: gen_ai.output.type
28
-
type: keyword
29
-
description: Represents the content type requested by the client.
30
-
example: text; json; image
31
-
- name: gen_ai.request.choice.count
32
-
type: integer
33
-
description: The target number of candidate completions to return.
34
-
example: 3
35
-
- name: gen_ai.request.encoding_formats
36
-
type: keyword[]
37
-
description: The encoding formats requested in an embeddings operation, if specified.
38
-
example: ["base64"]; ["float", "binary"]
39
-
- name: gen_ai.request.frequency_penalty
40
-
type: double
41
-
description: The frequency penalty setting for the GenAI request.
42
-
example: 0.1
43
-
- name: gen_ai.request.max_tokens
44
-
type: int
45
-
description: The maximum number of tokens the model generates for a request.
46
-
example: 100
47
-
- name: gen_ai.request.model
48
-
type: string
49
-
description: The name of the GenAI model a request is being made to.
50
-
example: gpt-4
51
-
- name: gen_ai.request.presence_penalty
52
-
type: double
53
-
description: The presence penalty setting for the GenAI request.
54
-
example: 0.1
55
-
- name: gen_ai.request.seed
56
-
type: integer
57
-
description: Requests with same seed value more likely to return same result.
58
-
example: 100
59
-
- name: gen_ai.request.stop_sequences
60
-
type: keyword[]
61
-
description: List of sequences that the model will use to stop generating further tokens.
62
-
example: ["forest", "lived"]
63
-
- name: gen_ai.request.temperature
64
-
type: double
65
-
description: The temperature setting for the GenAI request.
66
-
example: 0.0
67
-
- name: gen_ai.request.top_k
68
-
type: double
69
-
description: The top_k sampling setting for the GenAI request.
70
-
example: 1.0
71
-
- name: gen_ai.request.top_p
72
-
type: double
73
-
description: The top_p sampling setting for the GenAI request.
74
-
example: 1.0
75
-
- name: gen_ai.response.finish_reasons
76
-
type: keyword[]
77
-
description: Array of reasons the model stopped generating tokens, corresponding to each generation received.
78
-
example: ["stop"]; ["stop", "length"]
79
-
- name: gen_ai.response.id
80
-
type: keyword
81
-
description: The unique identifier for the completion.
82
-
example: chatcmpl-123
83
-
- name: gen_ai.response.model
84
-
type: keyword
85
-
description: The name of the model that generated the response.
86
-
example: gpt-4-0613
87
-
- name: gen_ai.system
88
-
type: keyword
89
-
description: The Generative AI product as identified by the client or server instrumentation.
90
-
example: openai
91
-
- name: gen_ai.token.type
92
-
type: keyword
93
-
description: The type of token being counted.
94
-
example: input; output
95
-
- name: gen_ai.tool.call.id
96
-
type: keyword
97
-
description: The tool call identifier.
98
-
example: call_mszuSIzqtI65i1wAUOE8w5H4
99
-
- name: gen_ai.tool.name
100
-
type: keyword
101
-
description: Name of the tool utilized by the agent.
102
-
example: Flights
103
-
- name: gen_ai.tool.type
104
-
type: keywo
105
-
description: Type of the tool utilized by the agent
106
-
example: function; extension; datastore
107
-
- name: gen_ai.usage.input_tokens
108
-
type: integer
109
-
description: The number of tokens used in the GenAI input (prompt).
110
-
example: 100
111
-
- name: gen_ai.usage.output_tokens
112
-
type: integer
113
-
description: The number of tokens used in the GenAI response (completion).
114
-
example: 180
11
+
- name: gen_ai.agent.description
12
+
type: text
13
+
description: Free-form description of the GenAI agent provided by the application.
14
+
example: Helps with math problems; Generates fiction stories
15
+
level: extended
16
+
beta: This field reuse is beta and subject to change.
17
+
otel:
18
+
- relation: match
19
+
- name: gen_ai.agent.id
20
+
type: keyword
21
+
description: The unique identifier of the GenAI agent.
22
+
example: asst_5j66UpCpwteGg4YSxUnt7lPY
23
+
level: extended
24
+
beta: This field reuse is beta and subject to change.
25
+
otel:
26
+
- relation: match
27
+
- name: gen_ai.agent.name
28
+
type: keyword
29
+
description: Human-readable name of the GenAI agent provided by the application.
30
+
example: Math Tutor; Fiction Writer
31
+
level: extended
32
+
beta: This field reuse is beta and subject to change.
33
+
otel:
34
+
- relation: match
35
+
- name: gen_ai.operation.name
36
+
type: keyword
37
+
description: The name of the operation being performed.
38
+
example: chat; text_completion; embeddings
39
+
level: extended
40
+
beta: This field reuse is beta and subject to change.
41
+
otel:
42
+
- relation: match
43
+
- name: gen_ai.output.type
44
+
type: keyword
45
+
description: Represents the content type requested by the client.
46
+
example: text; json; image
47
+
level: extended
48
+
beta: This field reuse is beta and subject to change.
49
+
otel:
50
+
- relation: match
51
+
- name: gen_ai.request.choice.count
52
+
type: integer
53
+
description: The target number of candidate completions to return.
54
+
example: 3
55
+
level: extended
56
+
beta: This field reuse is beta and subject to change.
57
+
otel:
58
+
- relation: match
59
+
- name: gen_ai.request.encoding_formats
60
+
type: nested
61
+
description: The encoding formats requested in an embeddings operation, if specified.
62
+
example: '["float", "binary"]'
63
+
level: extended
64
+
beta: This field reuse is beta and subject to change.
65
+
otel:
66
+
- relation: match
67
+
- name: gen_ai.request.frequency_penalty
68
+
type: double
69
+
description: The frequency penalty setting for the GenAI request.
70
+
example: 0.1
71
+
level: extended
72
+
beta: This field reuse is beta and subject to change.
73
+
otel:
74
+
- relation: match
75
+
- name: gen_ai.request.max_tokens
76
+
type: integer
77
+
description: The maximum number of tokens the model generates for a request.
78
+
example: 100
79
+
level: extended
80
+
beta: This field reuse is beta and subject to change.
81
+
otel:
82
+
- relation: match
83
+
- name: gen_ai.request.model
84
+
type: text
85
+
description: The name of the GenAI model a request is being made to.
86
+
example: gpt-4
87
+
level: extended
88
+
beta: This field reuse is beta and subject to change.
89
+
otel:
90
+
- relation: match
91
+
- name: gen_ai.request.presence_penalty
92
+
type: double
93
+
description: The presence penalty setting for the GenAI request.
94
+
example: 0.1
95
+
level: extended
96
+
beta: This field reuse is beta and subject to change.
97
+
otel:
98
+
- relation: match
99
+
- name: gen_ai.request.seed
100
+
type: integer
101
+
description: Requests with same seed value more likely to return same result.
102
+
example: 100
103
+
level: extended
104
+
beta: This field reuse is beta and subject to change.
105
+
otel:
106
+
- relation: match
107
+
- name: gen_ai.request.stop_sequences
108
+
type: nested
109
+
description: List of sequences that the model will use to stop generating further tokens.
110
+
example: '["forest", "lived"]'
111
+
level: extended
112
+
beta: This field reuse is beta and subject to change.
113
+
otel:
114
+
- relation: match
115
+
- name: gen_ai.request.temperature
116
+
type: double
117
+
description: The temperature setting for the GenAI request.
118
+
example: 0.0
119
+
level: extended
120
+
beta: This field reuse is beta and subject to change.
121
+
otel:
122
+
- relation: match
123
+
- name: gen_ai.request.top_k
124
+
type: double
125
+
description: The top_k sampling setting for the GenAI request.
126
+
example: 1.0
127
+
level: extended
128
+
beta: This field reuse is beta and subject to change.
129
+
otel:
130
+
- relation: match
131
+
- name: gen_ai.request.top_p
132
+
type: double
133
+
description: The top_p sampling setting for the GenAI request.
134
+
example: 1.0
135
+
level: extended
136
+
beta: This field reuse is beta and subject to change.
137
+
otel:
138
+
- relation: match
139
+
- name: gen_ai.response.finish_reasons
140
+
type: nested
141
+
description: Array of reasons the model stopped generating tokens, corresponding to each generation received.
142
+
example: '["stop", "length"]'
143
+
level: extended
144
+
beta: This field reuse is beta and subject to change.
145
+
otel:
146
+
- relation: match
147
+
- name: gen_ai.response.id
148
+
type: keyword
149
+
description: The unique identifier for the completion.
150
+
example: chatcmpl-123
151
+
level: extended
152
+
beta: This field reuse is beta and subject to change.
153
+
otel:
154
+
- relation: match
155
+
- name: gen_ai.response.model
156
+
type: keyword
157
+
description: The name of the model that generated the response.
158
+
example: gpt-4-0613
159
+
level: extended
160
+
beta: This field reuse is beta and subject to change.
161
+
otel:
162
+
- relation: match
163
+
- name: gen_ai.system
164
+
type: keyword
165
+
description: The Generative AI product as identified by the client or server instrumentation.
166
+
example: openai
167
+
level: extended
168
+
beta: This field reuse is beta and subject to change.
169
+
otel:
170
+
- relation: match
171
+
- name: gen_ai.token.type
172
+
type: keyword
173
+
description: The type of token being counted.
174
+
example: input; output
175
+
level: extended
176
+
beta: This field reuse is beta and subject to change.
177
+
otel:
178
+
- relation: match
179
+
- name: gen_ai.tool.call.id
180
+
type: keyword
181
+
description: The tool call identifier.
182
+
example: call_mszuSIzqtI65i1wAUOE8w5H4
183
+
level: extended
184
+
beta: This field reuse is beta and subject to change.
185
+
otel:
186
+
- relation: match
187
+
- name: gen_ai.tool.name
188
+
type: keyword
189
+
description: Name of the tool utilized by the agent.
190
+
example: Flights
191
+
level: extended
192
+
beta: This field reuse is beta and subject to change.
193
+
otel:
194
+
- relation: match
195
+
- name: gen_ai.tool.type
196
+
type: keyword
197
+
description: Type of the tool utilized by the agent
198
+
example: function; extension; datastore
199
+
level: extended
200
+
beta: This field reuse is beta and subject to change.
201
+
otel:
202
+
- relation: match
203
+
- name: gen_ai.usage.input_tokens
204
+
type: integer
205
+
description: The number of tokens used in the GenAI input (prompt).
206
+
example: 100
207
+
level: extended
208
+
beta: This field reuse is beta and subject to change.
209
+
otel:
210
+
- relation: match
211
+
- name: gen_ai.usage.output_tokens
212
+
type: integer
213
+
description: The number of tokens used in the GenAI response (completion).
214
+
example: 180
215
+
level: extended
216
+
beta: This field reuse is beta and subject to change.
0 commit comments