Skip to content

Update Weave reference documentation (Weave 0.53.4) #3000

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
github-actions wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Update Weave reference documentation (Weave 0.53.4) #3000

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions docs.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1231,6 +1231,7 @@
"weave/reference/typescript-sdk/functions/endllm",
"weave/reference/typescript-sdk/functions/endsession",
"weave/reference/typescript-sdk/functions/endturn",
"weave/reference/typescript-sdk/functions/flush",
"weave/reference/typescript-sdk/functions/flushotel",
"weave/reference/typescript-sdk/functions/getcurrentconversation",
"weave/reference/typescript-sdk/functions/getcurrentllm",
Expand Down Expand Up @@ -1263,6 +1264,7 @@
"weave/reference/typescript-sdk/interfaces/callschema",
"weave/reference/typescript-sdk/interfaces/callsfilter",
"weave/reference/typescript-sdk/interfaces/conversationinit",
"weave/reference/typescript-sdk/interfaces/customruntimeid",
"weave/reference/typescript-sdk/interfaces/getagentsoptions",
"weave/reference/typescript-sdk/interfaces/getagentspansoptions",
"weave/reference/typescript-sdk/interfaces/getagentturnoptions",
Expand All @@ -1275,6 +1277,7 @@
"weave/reference/typescript-sdk/interfaces/message",
"weave/reference/typescript-sdk/interfaces/query",
"weave/reference/typescript-sdk/interfaces/reasoning",
"weave/reference/typescript-sdk/interfaces/registercustomruntimeoptions",
"weave/reference/typescript-sdk/interfaces/sortby",
"weave/reference/typescript-sdk/interfaces/subagentinit",
"weave/reference/typescript-sdk/interfaces/toolinit",
Expand All @@ -1301,6 +1304,7 @@
"weave/reference/typescript-sdk/type-aliases/modality",
"weave/reference/typescript-sdk/type-aliases/op",
"weave/reference/typescript-sdk/type-aliases/opdecorator",
"weave/reference/typescript-sdk/type-aliases/registercustomruntimeresult",
"weave/reference/typescript-sdk/type-aliases/response",
"weave/reference/typescript-sdk/type-aliases/role",
"weave/reference/typescript-sdk/type-aliases/session",
Expand Down
4 changes: 2 additions & 2 deletions weave/guides/evaluation/evaluation_logger.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -447,11 +447,11 @@ Send the span to the same Weave project as the evaluation through the `/agents/o
For more information about the endpoint:

- To send spans from an existing OTel pipeline, see [Send OpenTelemetry spans to the Agents view](/weave/guides/tracking/trace-agents-otel).
- For the endpoint specification, see [Export a GenAI trace](/weave/reference/service-api/agents/export-genai-trace).
- For the endpoint specification, see [Export a GenAI trace](https://docs.wandb.ai/weave/reference/service-api/agents/export-genai-trace).

Only `weave.eval.run_id` and `weave.eval.predict_and_score_call_id` establish the evaluation and result links. The row digest, example ID, trial index, kind, and evaluation name add context and support filtering, but don't create a link by themselves. Use Weave Call IDs for the two linking attributes, not OTel trace or span IDs.

You can obtain both IDs from the [evaluation results query API](/weave/reference/service-api/eval-results/eval-results-query). Each evaluation in the response has an `evaluation_call_id`, and each trial has a `predict_and_score_call_id`.
You can obtain both IDs from the [evaluation results query API](https://docs.wandb.ai/weave/reference/service-api/eval-results/eval-results-query). Each evaluation in the response has an `evaluation_call_id`, and each trial has a `predict_and_score_call_id`.

The following examples assume that `span` is the OTel span for the agent operation. Replace each bracketed value with metadata from the evaluation run and result that the span belongs to.

Expand Down
Loading
Loading