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
Graphsignal is an observability platform for AI applications. It helps developers ensure AI applications run efficiently and provide the best user experience. With Graphsignal, developers can:
7
+
Graphsignal is an AI optimization platform, enabling developers to achieve faster, more efficient models and applications. With Graphsignal, developers can:
8
8
9
-
*Measure and optimize LLM performance for APIs and hosted models.
10
-
* Analyze model API costs for deployments, models, or any custom tags.
11
-
*View and search LLM generations with full context.
12
-
*Detect errors and monitor APIs, compute, and GPU utilization.
9
+
*Identify and optimize the most significant contributors to latency.
10
+
* Analyze model API costs for deployments, models, sessions, or any custom tags.
11
+
*Ensure optimal model configuration and inference performance for hosted models.
12
+
*Track errors and monitor APIs, compute, and GPU utilization.
To get an API key, sign up for a free account at [graphsignal.com](https://graphsignal.com). The key can then be found in your account's [Settings / API Keys](https://app.graphsignal.com/settings/api-keys) page.
40
40
41
-
Alternatively, you can add Graphsignal tracer at command line, when running your module or script. Environment variables `GRAPHSIGNAL_API_KEY` and `GRAPHSIGNAL_DEPLOYMENT` must be set.
41
+
Alternatively, you can add Graphsignal tracer from the command line, when running your module or script. Environment variables `GRAPHSIGNAL_API_KEY` and `GRAPHSIGNAL_DEPLOYMENT` must be set.
42
42
43
43
```bash
44
44
python -m graphsignal <script>
@@ -56,13 +56,14 @@ Graphsignal **auto-instruments** and traces libraries and frameworks, such as [O
56
56
Refer to the guides below for detailed information on:
*[Cost and Usage Monitoring](https://graphsignal.com/docs/guides/cost-and-usage-monitoring/)
61
62
*[Scores and Feedback](https://graphsignal.com/docs/guides/scores-and-feedback/)
62
63
63
64
See [API reference](https://graphsignal.com/docs/reference/python-api/) for full documentation.
64
65
65
-
Some integration examples are available in [examples](https://github.com/graphsignal/examples)repo.
66
+
Integration examples are available in [examples](https://github.com/graphsignal/examples)repository.
66
67
67
68
68
69
## Analyze
@@ -72,18 +73,18 @@ Some integration examples are available in [examples](https://github.com/graphsi
72
73
73
74
## Overhead
74
75
75
-
Graphsignal tracer is very lightweight. The overhead per trace is measured to be less than 100 microseconds.
76
+
Graphsignal tracer is highly lightweight. The overhead per trace is measured to be less than 100 microseconds.
76
77
77
78
78
79
## Security and Privacy
79
80
80
-
Graphsignal tracer can only open outbound connections to `api.graphsignal.com`and send data, no inbound connections or commands are possible.
81
+
The Graphsignal tracer only establishes outbound connections to `api.graphsignal.com`to send data; inbound connections or commands are not possible.
81
82
82
83
Payloads, such as prompts and completions, are recorded by default in case of automatic tracing. To disable, set `record_payloads=False` in `graphsignal.configure`.
83
84
84
85
85
86
## Troubleshooting
86
87
87
-
To enable debug logging, add `debug_mode=True` to `configure()`. If the debug log doesn't give you any hints on how to fix a problem, please report it to our support team via your account.
88
+
To enable debug logging, add `debug_mode=True` to `configure()`. If the debug log doesn’t provide hints for resolving the issue, report it to our support team via your account.
88
89
89
90
In case of connection issues, please make sure outgoing connections to `https://api.graphsignal.com` are allowed.
0 commit comments