|
Up
|
|
|
|
|
1-define-your-evaluation-dataset-2.md
|
|
|
|
|
1-define-your-evaluation-dataset.md
|
|
|
|
|
1-export-data-in-csv-format-for-analysis.md
|
|
|
|
|
1-export-specific-data-from-source-workspace-json-format.md
|
|
|
|
|
1-import-our-agent-class.md
|
|
|
|
|
1-start-be-only-mode-fastest-for-backend-work.md
|
|
|
|
|
1-start-infrastructure-only.md
|
|
|
|
|
1-start-local-process-mode-2.md
|
|
|
|
|
1-start-local-process-mode.md
|
|
|
|
|
2-configure-the-evaluation-metric-must-return-reasons.md
|
|
|
|
|
2-configure-the-evaluation-metric.md
|
|
|
|
|
2-define-our-llm-configuration-for-openais-gpt-4o-mini.md
|
|
|
|
|
2-inspect-the-csv-files.md
|
|
|
|
|
2-inspect-the-exported-data.md
|
|
|
|
|
2-run-tests-against-full-environment.md
|
|
|
|
|
2-start-backend-separately-if-needed.md
|
|
|
|
|
3-analyze-with-pandas-optional.md
|
|
|
|
|
3-clean-up.md
|
|
|
|
|
3-create-our-llm-agent-within-the-parent-span-context.md
|
|
|
|
|
3-define-your-base-prompt-and-task-configuration.md
|
|
|
|
|
3-define-your-initial-prompt.md
|
|
|
|
|
3-dry-run-import-to-see-what-would-be-imported.md
|
|
|
|
|
3-rebuild-and-restart-backend.md
|
|
|
|
|
3-test-at-httplocalhost5174.md
|
|
|
|
|
3-view-changes-at-httplocalhost5174.md
|
|
|
|
|
4-actually-import-all-data-including-experiments-and-prompts.md
|
|
|
|
|
4-for-import-you-would-need-to-convert-back-to-json-format.md
|
|
|
|
|
4-initialize-hrpo.md
|
|
|
|
|
4-initialize-the-evolutionaryoptimizer.md
|
|
|
|
|
4-run-clickhouse-migrations.md
|
|
|
|
|
4-test-changes-via-ui-at-httplocalhost5173.md
|
|
|
|
|
4-test-sdk-changes.md
|
|
|
|
|
5-clean-up-temporary-data.md
|
|
|
|
|
5-run-the-optimization-2.md
|
|
|
|
|
5-run-the-optimization.md
|
|
|
|
|
6-view-the-results-2.md
|
|
|
|
|
6-view-the-results.md
|
|
|
|
|
access-results-2.md
|
|
|
|
|
access-results-3.md
|
|
|
|
|
access-results.md
|
|
|
|
|
access-the-response-data.md
|
|
|
|
|
access-the-rest-api-client.md
|
|
|
|
|
add-answer-column-llm-generated.md
|
|
|
|
|
add-conditional-routing.md
|
|
|
|
|
add-difficulty-column.md
|
|
|
|
|
add-experiment-results.md
|
|
|
|
|
add-feedback-to-a-trace.md
|
|
|
|
|
add-guardrails-services.md
|
|
|
|
|
add-items-to-annotation-queue.md
|
|
|
|
|
add-items-to-the-dataset.md
|
|
|
|
|
add-multiple-anonymizers-in-order.md
|
|
|
|
|
add-opik-tracking-2.md
|
|
|
|
|
add-opik-tracking.md
|
|
|
|
|
add-question-column-llm-generated.md
|
|
|
|
|
add-span-comment.md
|
|
|
|
|
add-span-feedback-score.md
|
|
|
|
|
add-the-exporter-to-the-tracer-provider.md
|
|
|
|
|
add-the-opikconnector-component-to-the-pipeline.md
|
|
|
|
|
add-the-prompt-template-as-an-experiment-configuration-2.md
|
|
|
|
|
add-the-prompt-template-as-an-experiment-configuration.md
|
|
|
|
|
add-the-user-message.md
|
|
|
|
|
add-thread-comment.md
|
|
|
|
|
add-topic-column-categorical-sampler.md
|
|
|
|
|
add-trace-comment.md
|
|
|
|
|
add-trace-feedback-score.md
|
|
|
|
|
adk-session-management.md
|
|
|
|
|
advanced-clickhouse-backup.md
|
|
|
|
|
advanced-configuration-2.md
|
|
|
|
|
advanced-configuration.md
|
|
|
|
|
advanced-deployment-options.md
|
|
|
|
|
after-optimization-test-on-unseen-data.md
|
|
|
|
|
agent-framework-2-packages.md
|
|
|
|
|
agent-optimization.md
|
|
|
|
|
agent-task-completion-judge.md
|
|
|
|
|
agent-task-completion.md
|
|
|
|
|
agent-tool-correctness-judge.md
|
|
|
|
|
agent-tool-correctness.md
|
|
|
|
|
ai-providers.md
|
|
|
|
|
alerts.md
|
|
|
|
|
all-inputs-and-outputs-will-be-automatically-anonymized.md
|
|
|
|
|
all-services-except-backend-for-local-backend-development.md
|
|
|
|
|
all-traces-will-be-automatically-grouped-by-session-id-as-thread-id.md
|
|
|
|
|
all-traces-with-the-same-thread-id-will-be-grouped-together.md
|
|
|
|
|
alternative-export-experiment-with-specific-dataset-filtering.md
|
|
|
|
|
analyze-an-image-from-a-url.md
|
|
|
|
|
analyze-sentiment.md
|
|
|
|
|
analyze-the-json-files-locally.md
|
|
|
|
|
annotate-traces.md
|
|
|
|
|
annotation-queues.md
|
|
|
|
|
anonymizers.md
|
|
|
|
|
anonymous-usage-statistics.md
|
|
|
|
|
answer-relevance.md
|
|
|
|
|
apply-changes-to-dataset-items.md
|
|
|
|
|
apprb.md
|
|
|
|
|
april-14-2025.md
|
|
|
|
|
april-21-2025.md
|
|
|
|
|
april-28-2025.md
|
|
|
|
|
april-7-2025.md
|
|
|
|
|
arc-agi-optimization-tutorial.md
|
|
|
|
|
asynchronous-execution-requires-explicit-trace-context-propagation.md
|
|
|
|
|
attachments-list-for-entity.md
|
|
|
|
|
attempting-to-create-a-text-prompt-with-the-same-name-will-raise-an-error.md
|
|
|
|
|
august-1-2025.md
|
|
|
|
|
august-22-2025.md
|
|
|
|
|
available-candidate-generation-reasoning-system.md
|
|
|
|
|
backend-changes-require-rebuild.md
|
|
|
|
|
backend.md
|
|
|
|
|
basic-setup.md
|
|
|
|
|
batch-feedback-scoring-for-spans.md
|
|
|
|
|
batch-feedback-scoring-for-threads.md
|
|
|
|
|
batch-feedback-scoring-for-traces.md
|
|
|
|
|
batch-update-dataset-items.md
|
|
|
|
|
batch-update-experiments.md
|
|
|
|
|
batch-update-spans.md
|
|
|
|
|
batch-update-threads.md
|
|
|
|
|
batch-update-traces.md
|
|
|
|
|
be-only-mode.md
|
|
|
|
|
best-practices-for-evaluating-agents.md
|
|
|
|
|
best-practices.md
|
|
|
|
|
bounty-program.md
|
|
|
|
|
brand-mention-detection.md
|
|
|
|
|
build-and-execute-graph-2.md
|
|
|
|
|
build-and-execute-graph-3.md
|
|
|
|
|
build-and-execute-graph.md
|
|
|
|
|
build-and-run.md
|
|
|
|
|
build-and-start-all-services-recommended-for-first-time.md
|
|
|
|
|
build-backend-only.md
|
|
|
|
|
build-frontend-only.md
|
|
|
|
|
build-the-opik-platform-from-source.md
|
|
|
|
|
call-the-local-ollama-model-using-the-openai-client.md
|
|
|
|
|
call-the-ollama-model.md
|
|
|
|
|
call-the-tracked-function-2.md
|
|
|
|
|
call-the-tracked-function.md
|
|
|
|
|
calling-langchain-object-2.md
|
|
|
|
|
calling-langchain-object.md
|
|
|
|
|
calling-langgraph-stream-or-invoke-functions.md
|
|
|
|
|
cancel-studio-optimizations.md
|
|
|
|
|
chaining-optimizers.md
|
|
|
|
|
change-from.md
|
|
|
|
|
changelog.md
|
|
|
|
|
chatprompt-model-this-is-the-model-your-prompt-runs-on.md
|
|
|
|
|
check-backup-job-logs.md
|
|
|
|
|
check-backup-server-logs.md
|
|
|
|
|
check-clickhouse-is-accessible.md
|
|
|
|
|
check-cronjob-status.md
|
|
|
|
|
check-docker.md
|
|
|
|
|
check-if-any-anonymizers-are-registered.md
|
|
|
|
|
check-mysql-is-accessible.md
|
|
|
|
|
check-nodejs-and-npm.md
|
|
|
|
|
check-port-conflicts.md
|
|
|
|
|
check-python.md
|
|
|
|
|
check-status.md
|
|
|
|
|
check-system-health.md
|
|
|
|
|
check-the-scripts-directory-for-working-examples.md
|
|
|
|
|
check-user-access-to-workspace.md
|
|
|
|
|
clean-backend-build.md
|
|
|
|
|
clean-frontend-build.md
|
|
|
|
|
clear-existing-anonymizers.md
|
|
|
|
|
clickhouse-backup-guide.md
|
|
|
|
|
clone-and-navigate-to-the-example.md
|
|
|
|
|
clone-the-opik-repository.md
|
|
|
|
|
close-trace-threads.md
|
|
|
|
|
comet-docs-opik-documentation.md
|
|
|
|
|
compare-latest-version-with-draft.md
|
|
|
|
|
complete-cleanup-and-restart.md
|
|
|
|
|
complete-multipart-attachment-upload.md
|
|
|
|
|
compliance-risk-judge.md
|
|
|
|
|
compliance-risk.md
|
|
|
|
|
comprehensive-evaluation-approach.md
|
|
|
|
|
concepts.md
|
|
|
|
|
configuration-options.md
|
|
|
|
|
configuration.md
|
|
|
|
|
configure-anonymization-mix-regex-and-callable-function.md
|
|
|
|
|
configure-for-vertexai-required-for-veo.md
|
|
|
|
|
configure-for-vertexai.md
|
|
|
|
|
configure-litellm-for-opik-2.md
|
|
|
|
|
configure-litellm-for-opik.md
|
|
|
|
|
configure-model-parameters-for-the-chatprompt.md
|
|
|
|
|
configure-model-parameters-for-the-optimizer.md
|
|
|
|
|
configure-openai-llm-with-stream-options-to-include-usage-information.md
|
|
|
|
|
configure-opik-2.md
|
|
|
|
|
configure-opik-3.md
|
|
|
|
|
configure-opik-integration-2.md
|
|
|
|
|
configure-opik-integration-3.md
|
|
|
|
|
configure-opik-integration-for-llm-calls-within-steps.md
|
|
|
|
|
configure-opik-integration.md
|
|
|
|
|
configure-opik-tracer-2.md
|
|
|
|
|
configure-opik-tracer-for-hybrid-example.md
|
|
|
|
|
configure-opik-tracer-for-multi-agent-example.md
|
|
|
|
|
configure-opik-tracer-same-as-before.md
|
|
|
|
|
configure-opik-tracer.md
|
|
|
|
|
configure-opik.md
|
|
|
|
|
configure-the-agent.md
|
|
|
|
|
configure-the-bedrock-model-to-be-used-by-the-agent.md
|
|
|
|
|
configure-the-opik-tracer.md
|
|
|
|
|
configure-the-otlp-exporter-for-opik.md
|
|
|
|
|
configure-the-python-sdk-to-point-to-the-local-opik-platform.md
|
|
|
|
|
configure-the-tracer-provider-2.md
|
|
|
|
|
configure-the-tracer-provider.md
|
|
|
|
|
configured-automatically-from-env.md
|
|
|
|
|
configuring-llm-providers.md
|
|
|
|
|
connect-to-clickhouse.md
|
|
|
|
|
connect-to-first-replica.md
|
|
|
|
|
connect-to-second-replica-if-running-multiple-replicas.md
|
|
|
|
|
connect-to-the-first-clickhouse-replica.md
|
|
|
|
|
connect-to-zookeeper-cli.md
|
|
|
|
|
connect-to-zookeeper-pod-2.md
|
|
|
|
|
connect-to-zookeeper-pod.md
|
|
|
|
|
console-logging-reduce-noise.md
|
|
|
|
|
console-show-only-warnings-and-errors.md
|
|
|
|
|
context-precision.md
|
|
|
|
|
context-recall.md
|
|
|
|
|
continue-building-the-pipeline.md
|
|
|
|
|
contributing-to-documentation.md
|
|
|
|
|
contributing-to-opik.md
|
|
|
|
|
contributing-to-the-agent-optimizer-sdk.md
|
|
|
|
|
contributing-to-the-backend.md
|
|
|
|
|
contributing-to-the-frontend.md
|
|
|
|
|
contributing-to-the-opik-python-sdk.md
|
|
|
|
|
contributing-to-the-typescript-sdk.md
|
|
|
|
|
contribution-overview.md
|
|
|
|
|
conversational-metrics.md
|
|
|
|
|
convert-to-opik-format-2.md
|
|
|
|
|
convert-to-opik-format-3.md
|
|
|
|
|
convert-to-opik-format-4.md
|
|
|
|
|
convert-to-opik-format-5.md
|
|
|
|
|
convert-to-opik-format-6.md
|
|
|
|
|
convert-to-opik-format.md
|
|
|
|
|
cookbook-evaluate-hallucination-metric.md
|
|
|
|
|
cookbook-evaluate-moderation-metric.md
|
|
|
|
|
coordinator-agent-with-sub-agents.md
|
|
|
|
|
correct.md
|
|
|
|
|
cost-tracking.md
|
|
|
|
|
create-a-backup.md
|
|
|
|
|
create-a-chat-prompt.md
|
|
|
|
|
create-a-dataset-that-contains-the-samples-you-want-to-evaluate.md
|
|
|
|
|
create-a-manual-trace.md
|
|
|
|
|
create-a-new-dataset.md
|
|
|
|
|
create-a-react-agent-with-memory.md
|
|
|
|
|
create-a-simple-agent.md
|
|
|
|
|
create-a-simple-dataset.md
|
|
|
|
|
create-a-small-dataset.md
|
|
|
|
|
create-a-trace-and-spans-via-opentelemetry-instrumentation.md
|
|
|
|
|
create-a-trace.md
|
|
|
|
|
create-a-tracer-provider.md
|
|
|
|
|
create-alert.md
|
|
|
|
|
create-an-evaluation-task.md
|
|
|
|
|
create-an-experiment-linked-to-a-dataset.md
|
|
|
|
|
create-an-openai-client-configured-for-portkey.md
|
|
|
|
|
create-an-openai-client-with-anannas-ais-base-url.md
|
|
|
|
|
create-an-openai-client-with-helicones-base-url.md
|
|
|
|
|
create-an-openai-client-with-truefoundrys-base-url.md
|
|
|
|
|
create-an-openai-client-with-vercel-ai-gateways-base-url.md
|
|
|
|
|
create-an-openai-client.md
|
|
|
|
|
create-and-configure-the-agent.md
|
|
|
|
|
create-and-register-anonymizer.md
|
|
|
|
|
create-and-use-the-advanced-agent.md
|
|
|
|
|
create-and-wrap-the-openai-client-with-anannas-ais-base-url.md
|
|
|
|
|
create-and-wrap-the-openai-client-with-helicones-base-url.md
|
|
|
|
|
create-and-wrap-the-openai-client-with-truefoundrys-base-url.md
|
|
|
|
|
create-and-wrap-the-openai-client-with-vercel-ai-gateways-base-url.md
|
|
|
|
|
create-annotation-queue-batch.md
|
|
|
|
|
create-annotation-queue.md
|
|
|
|
|
create-anonymizer-with-function-rules.md
|
|
|
|
|
create-anonymizer-with-multiple-rules.md
|
|
|
|
|
create-automation-rule-evaluator.md
|
|
|
|
|
create-backup-of-specific-data-requires-knowing-exact-names.md
|
|
|
|
|
create-chat-completions.md
|
|
|
|
|
create-dashboard.md
|
|
|
|
|
create-dataset-2.md
|
|
|
|
|
create-dataset-3.md
|
|
|
|
|
create-dataset-4.md
|
|
|
|
|
create-dataset-5.md
|
|
|
|
|
create-dataset-in-opik-2.md
|
|
|
|
|
create-dataset-in-opik.md
|
|
|
|
|
create-dataset-items-from-csv-file.md
|
|
|
|
|
create-dataset-items-from-spans.md
|
|
|
|
|
create-dataset-items-from-traces.md
|
|
|
|
|
create-dataset-redirect-url.md
|
|
|
|
|
create-dataset.md
|
|
|
|
|
create-directory-if-it-doesnt-exist.md
|
|
|
|
|
create-evaluation-datasets.md
|
|
|
|
|
create-experiment-items.md
|
|
|
|
|
create-experiment-redirect-url.md
|
|
|
|
|
create-experiment.md
|
|
|
|
|
create-feedback-definition.md
|
|
|
|
|
create-guardrails-for-traces-in-a-batch.md
|
|
|
|
|
create-hybrid-agent-that-combines-both-tracing-approaches.md
|
|
|
|
|
create-opiktracer-and-track-the-graph-once-no-need-to-pass-callbacks-anymore.md
|
|
|
|
|
create-optimization-redirect-url.md
|
|
|
|
|
create-optimization.md
|
|
|
|
|
create-optimizer-with-customizations.md
|
|
|
|
|
create-predibase-model.md
|
|
|
|
|
create-project-redirect-url.md
|
|
|
|
|
create-project.md
|
|
|
|
|
create-prompt-2.md
|
|
|
|
|
create-prompt-version.md
|
|
|
|
|
create-prompt-with-n3-for-variety.md
|
|
|
|
|
create-prompt.md
|
|
|
|
|
create-sample-qa-data-needs-200-records-for-holdout.md
|
|
|
|
|
create-span.md
|
|
|
|
|
create-spans.md
|
|
|
|
|
create-synthetic-questions-using-openai.md
|
|
|
|
|
create-the-agent-with-explicit-callback-configuration.md
|
|
|
|
|
create-the-answer-relevancy-scoring-metric.md
|
|
|
|
|
create-the-basic-agent-2.md
|
|
|
|
|
create-the-basic-agent.md
|
|
|
|
|
create-the-crew.md
|
|
|
|
|
create-the-dataset.md
|
|
|
|
|
create-the-hallucination-metric-2.md
|
|
|
|
|
create-the-hallucination-metric-3.md
|
|
|
|
|
create-the-hallucination-metric-4.md
|
|
|
|
|
create-the-hallucination-metric.md
|
|
|
|
|
create-the-langchain-chain-with-opiktracer.md
|
|
|
|
|
create-the-node-functions.md
|
|
|
|
|
create-the-ollama-model-and-configure-it-to-use-the-opik-tracer.md
|
|
|
|
|
create-the-opik-tracer-2.md
|
|
|
|
|
create-the-opik-tracer.md
|
|
|
|
|
create-the-opiktracer-and-track-the-graph.md
|
|
|
|
|
create-the-opiktracer.md
|
|
|
|
|
create-the-workflow.md
|
|
|
|
|
create-tools-for-the-agent.md
|
|
|
|
|
create-trace.md
|
|
|
|
|
create-traces.md
|
|
|
|
|
create-training-dataset-70-80-of-your-data.md
|
|
|
|
|
create-validation-dataset-20-30-of-your-data.md
|
|
|
|
|
create-version-tag.md
|
|
|
|
|
create-workflow-instance.md
|
|
|
|
|
create-your-langgraph-graph-2.md
|
|
|
|
|
create-your-langgraph-graph-3.md
|
|
|
|
|
create-your-langgraph-graph.md
|
|
|
|
|
create-your-openai-client.md
|
|
|
|
|
createupdate-dataset-items.md
|
|
|
|
|
csv-format-is-primarily-for-analysis-not-import.md
|
|
|
|
|
custom-conversation-metric.md
|
|
|
|
|
custom-conversation-multi-turn-metrics.md
|
|
|
|
|
custom-metric-2.md
|
|
|
|
|
custom-metric-one-templateprompt-to-extract-4-scoresresults.md
|
|
|
|
|
custom-metric.md
|
|
|
|
|
custom-metrics.md
|
|
|
|
|
custom-model.md
|
|
|
|
|
custom-optimizer-prompts.md
|
|
|
|
|
dashboard-results.md
|
|
|
|
|
dashboards.md
|
|
|
|
|
dataset-versioning-migration-2.md
|
|
|
|
|
dataset-versioning-migration.md
|
|
|
|
|
datasets.md
|
|
|
|
|
debug-mode.md
|
|
|
|
|
december-16-2024.md
|
|
|
|
|
december-18-2025.md
|
|
|
|
|
december-2-2024.md
|
|
|
|
|
december-23-2024.md
|
|
|
|
|
december-30-2024.md
|
|
|
|
|
december-9-2024.md
|
|
|
|
|
december-9-2025.md
|
|
|
|
|
deepgram-api.md
|
|
|
|
|
default-max-depth-is-10.md
|
|
|
|
|
define-a-model-client-you-can-use-other-model-client-that-implements.md
|
|
|
|
|
define-a-research-assistant-prompt-with-tools.md
|
|
|
|
|
define-a-simple-function-tool-that-the-agent-can-use.md
|
|
|
|
|
define-an-assistantagent-with-the-model-tool-system-message-and-reflection.md
|
|
|
|
|
define-both-prompts-in-the-workflow.md
|
|
|
|
|
define-datasets.md
|
|
|
|
|
define-evaluation-metric.md
|
|
|
|
|
define-evaluation-metrics.md
|
|
|
|
|
define-metric-2.md
|
|
|
|
|
define-metric-and-prompt-see-docs-for-more-options.md
|
|
|
|
|
define-metric-and-task-configuration-see-docs-for-more-options.md
|
|
|
|
|
define-metric.md
|
|
|
|
|
define-metrics.md
|
|
|
|
|
define-multi-prompt-workflow.md
|
|
|
|
|
define-parameter-search-space.md
|
|
|
|
|
define-pii-anonymization-rules.md
|
|
|
|
|
define-prompt-this-stays-unchanged.md
|
|
|
|
|
define-the-evaluation-task-2.md
|
|
|
|
|
define-the-evaluation-task-3.md
|
|
|
|
|
define-the-evaluation-task.md
|
|
|
|
|
define-the-graph-state.md
|
|
|
|
|
define-the-items.md
|
|
|
|
|
define-the-metrics.md
|
|
|
|
|
define-the-scoring-metric-2.md
|
|
|
|
|
define-the-scoring-metric.md
|
|
|
|
|
define-the-system-prompt-for-the-agent.md
|
|
|
|
|
define-the-task-to-evaluate.md
|
|
|
|
|
define-your-crew-using-the-example-from-above.md
|
|
|
|
|
define-your-desired-output-structure.md
|
|
|
|
|
define-your-evaluation-task-2.md
|
|
|
|
|
define-your-evaluation-task-3.md
|
|
|
|
|
define-your-evaluation-task-4.md
|
|
|
|
|
define-your-evaluation-task.md
|
|
|
|
|
define-your-own-cost-mapping-for-different-models.md
|
|
|
|
|
define-your-rules.md
|
|
|
|
|
delete-alert-batch.md
|
|
|
|
|
delete-all-clickhouse-table-paths.md
|
|
|
|
|
delete-annotation-queue-batch.md
|
|
|
|
|
delete-attachments.md
|
|
|
|
|
delete-automation-rule-evaluators.md
|
|
|
|
|
delete-dashboard.md
|
|
|
|
|
delete-dashboards.md
|
|
|
|
|
delete-dataset-by-id.md
|
|
|
|
|
delete-dataset-by-name.md
|
|
|
|
|
delete-dataset-items.md
|
|
|
|
|
delete-datasets.md
|
|
|
|
|
delete-experiment-items.md
|
|
|
|
|
delete-experiments-by-id.md
|
|
|
|
|
delete-feedback-definition-by-id.md
|
|
|
|
|
delete-feedback-definitions.md
|
|
|
|
|
delete-llm-providers-apikeys.md
|
|
|
|
|
delete-optimizations-by-id.md
|
|
|
|
|
delete-project-by-id.md
|
|
|
|
|
delete-projects.md
|
|
|
|
|
delete-prompt.md
|
|
|
|
|
delete-prompts.md
|
|
|
|
|
delete-span-by-id.md
|
|
|
|
|
delete-span-comments.md
|
|
|
|
|
delete-span-feedback-score.md
|
|
|
|
|
delete-thread-comments.md
|
|
|
|
|
delete-thread-feedback-scores.md
|
|
|
|
|
delete-trace-by-id.md
|
|
|
|
|
delete-trace-comments.md
|
|
|
|
|
delete-trace-feedback-score.md
|
|
|
|
|
delete-trace-threads.md
|
|
|
|
|
delete-traces.md
|
|
|
|
|
delete-version-tag.md
|
|
|
|
|
delete-workspace-configuration.md
|
|
|
|
|
delete-your-installation.md
|
|
|
|
|
dependencies-opentelemetry-exporter-otlp.md
|
|
|
|
|
deprecated.md
|
|
|
|
|
df-pdread-csvanalysis-datamy-workspaceprojectsmy-projecttraces-my-projectcsv.md
|
|
|
|
|
dialogue-helpfulness-judge.md
|
|
|
|
|
dialogue-helpfulness.md
|
|
|
|
|
dictionary-format.md
|
|
|
|
|
different-profiles.md
|
|
|
|
|
directly-using-langchain-message-objects.md
|
|
|
|
|
disable-after-successful-migration.md
|
|
|
|
|
disable-io-capture-for-privacy.md
|
|
|
|
|
disable-metrics-and-logs-exporters-via-opentelemetry-to-avoid-putting-an-extra-l.md
|
|
|
|
|
docker-compose-2.md
|
|
|
|
|
docker-compose-3.md
|
|
|
|
|
docker-compose-4.md
|
|
|
|
|
docker-compose.md
|
|
|
|
|
documentation.md
|
|
|
|
|
download-an-attachment.md
|
|
|
|
|
download-and-set-up-the-chinook-database.md
|
|
|
|
|
download-attachment-from-minio.md
|
|
|
|
|
download-backup-from-s3.md
|
|
|
|
|
download-dataset-export-file.md
|
|
|
|
|
download-the-file-using-requests.md
|
|
|
|
|
dry-run-to-see-what-would-be-imported.md
|
|
|
|
|
each-trace-is-exported-to-its-own-csv-file.md
|
|
|
|
|
enable-async-support-in-jupyter-notebooks.md
|
|
|
|
|
enable-debug-logging.md
|
|
|
|
|
enable-openai-tracking-with-automatic-anonymization.md
|
|
|
|
|
enable-opentelemetry-tracing.md
|
|
|
|
|
enable-port-mapping-useful-for-debugging.md
|
|
|
|
|
enable-tracing-in-your-pipelinetask.md
|
|
|
|
|
enable-tracking-with-the-crew-instance-required-for-v100.md
|
|
|
|
|
enable-verbose-logging.md
|
|
|
|
|
enabled-the-system-message-instructs-the-agent-via-natural-language.md
|
|
|
|
|
enabling-large-csv-uploads.md
|
|
|
|
|
ensure-all-traces-are-sent-before-script-exits.md
|
|
|
|
|
ensure-these-are-set-securely-eg-via-environment-variables.md
|
|
|
|
|
evaluate-agent-trajectories.md
|
|
|
|
|
evaluate-function.md
|
|
|
|
|
evaluate-llm-applications-with-ragas-metrics-in-opik.md
|
|
|
|
|
evaluate-multi-turn-agents.md
|
|
|
|
|
evaluate-multimodal-traces.md
|
|
|
|
|
evaluate-on-your-dataset-2.md
|
|
|
|
|
evaluate-on-your-dataset.md
|
|
|
|
|
evaluate-single-prompts.md
|
|
|
|
|
evaluate-threads-in-your-project-2.md
|
|
|
|
|
evaluate-threads-in-your-project.md
|
|
|
|
|
evaluate-threads.md
|
|
|
|
|
evaluate-your-agent.md
|
|
|
|
|
evaluate-your-llm-application.md
|
|
|
|
|
evaluateprompt-function.md
|
|
|
|
|
evaluating-opiks-hallucination-metric.md
|
|
|
|
|
evaluating-opiks-moderation-metric.md
|
|
|
|
|
evaluation-concepts-and-overview.md
|
|
|
|
|
evaluation-metrics.md
|
|
|
|
|
evaluation.md
|
|
|
|
|
evolutionary-optimizer-genetic-algorithms.md
|
|
|
|
|
example-conversation.md
|
|
|
|
|
example-metric-under-test.md
|
|
|
|
|
example-paginated-response.md
|
|
|
|
|
example-prometheus-alerts.md
|
|
|
|
|
example-queries.md
|
|
|
|
|
example-reading-a-file-into-memory-and-logging-it.md
|
|
|
|
|
example-usage-2.md
|
|
|
|
|
example-usage-3.md
|
|
|
|
|
example-usage-4.md
|
|
|
|
|
example-usage-5.md
|
|
|
|
|
example-usage-6.md
|
|
|
|
|
example-usage-7.md
|
|
|
|
|
example-usage-in-a-cron-job.md
|
|
|
|
|
example-usage-pii-will-be-automatically-anonymized-in-traces.md
|
|
|
|
|
example-usage.md
|
|
|
|
|
examples-of-the-litellm-model-format.md
|
|
|
|
|
exclude-noisy-nodes.md
|
|
|
|
|
execute-commands-in-containers.md
|
|
|
|
|
execute-the-multi-step-pipeline-2.md
|
|
|
|
|
execute-the-multi-step-pipeline-3.md
|
|
|
|
|
execute-the-multi-step-pipeline-4.md
|
|
|
|
|
execute-the-multi-step-pipeline-5.md
|
|
|
|
|
execute-the-multi-step-pipeline-6.md
|
|
|
|
|
execute-the-multi-step-pipeline-7.md
|
|
|
|
|
execute-the-multi-step-pipeline.md
|
|
|
|
|
execute-the-workflow-no-callbacks-needed.md
|
|
|
|
|
expand-dataset-with-synthetic-samples.md
|
|
|
|
|
experiments.md
|
|
|
|
|
export-all-data-from-source-project.md
|
|
|
|
|
export-another-prompt-template.md
|
|
|
|
|
export-by-sdk-rest-and-ui.md
|
|
|
|
|
export-datasets-in-csv-format-for-analysis-2.md
|
|
|
|
|
export-datasets-in-csv-format-for-analysis.md
|
|
|
|
|
export-experiment-with-dataset-filtering-2.md
|
|
|
|
|
export-experiment-with-dataset-filtering.md
|
|
|
|
|
export-experiment-with-trace-limit-useful-for-large-experiments.md
|
|
|
|
|
export-experiment-with-trace-limit.md
|
|
|
|
|
export-experiments-in-csv-format-for-analysis-2.md
|
|
|
|
|
export-experiments-in-csv-format-for-analysis.md
|
|
|
|
|
export-prompts-in-csv-format-for-analysis-2.md
|
|
|
|
|
export-prompts-in-csv-format-for-analysis.md
|
|
|
|
|
export-specific-dataset-by-exact-name.md
|
|
|
|
|
export-specific-dataset-from-a-workspace.md
|
|
|
|
|
export-specific-experiment-by-exact-name.md
|
|
|
|
|
export-specific-experiment-from-source-workspace.md
|
|
|
|
|
export-specific-project-by-exact-name.md
|
|
|
|
|
export-specific-prompt-by-exact-name.md
|
|
|
|
|
export-specific-prompt-from-a-workspace.md
|
|
|
|
|
export-specific-traces-for-analysis.md
|
|
|
|
|
export-traces-in-csv-format-for-analysis-2.md
|
|
|
|
|
export-traces-in-csv-format-for-analysis.md
|
|
|
|
|
export-using-default-directory-opik-exports.md
|
|
|
|
|
export-with-custom-output-directory.md
|
|
|
|
|
export-with-debug-output.md
|
|
|
|
|
export-with-filter-and-limit.md
|
|
|
|
|
extending-optimizers.md
|
|
|
|
|
extra-dependencies-you-want-to-provide-to-the-task.md
|
|
|
|
|
faq.md
|
|
|
|
|
february-10-2025.md
|
|
|
|
|
february-17-2025.md
|
|
|
|
|
february-24-2025.md
|
|
|
|
|
february-3-2025.md
|
|
|
|
|
feedback-definitions.md
|
|
|
|
|
few-shot-bayesian-optimizer.md
|
|
|
|
|
file-log-everything-for-debugging.md
|
|
|
|
|
file-logging-for-debug.md
|
|
|
|
|
final-flush-to-ensure-all-traces-are-logged.md
|
|
|
|
|
find-alerts.md
|
|
|
|
|
find-annotation-queues.md
|
|
|
|
|
find-dashboards.md
|
|
|
|
|
find-dataset-items-with-experiment-items.md
|
|
|
|
|
find-datasets.md
|
|
|
|
|
find-experiment-groups-with-aggregations.md
|
|
|
|
|
find-experiment-groups.md
|
|
|
|
|
find-experiments.md
|
|
|
|
|
find-feedback-definitions.md
|
|
|
|
|
find-feedback-score-names-2.md
|
|
|
|
|
find-feedback-score-names-3.md
|
|
|
|
|
find-feedback-score-names-by-project-ids.md
|
|
|
|
|
find-feedback-score-names.md
|
|
|
|
|
find-llm-providers-apikeys.md
|
|
|
|
|
find-optimizations.md
|
|
|
|
|
find-project-evaluators.md
|
|
|
|
|
find-projects.md
|
|
|
|
|
find-token-usage-names.md
|
|
|
|
|
find-trace-threads-feedback-score-names.md
|
|
|
|
|
finish-experiments.md
|
|
|
|
|
fireworks-ai-configuration.md
|
|
|
|
|
first-we-will-configure-the-opentelemetry.md
|
|
|
|
|
flush-traces-to-ensure-all-data-is-logged.md
|
|
|
|
|
follow-logs-in-real-time.md
|
|
|
|
|
for-claude-code-users-syncs-rules-to-claude-and-generates-mcpjson.md
|
|
|
|
|
for-comet-hosted-installations.md
|
|
|
|
|
for-cometcom.md
|
|
|
|
|
for-cursor-users-creates-cursor-symlink-to-agents.md
|
|
|
|
|
for-local-development-you-can-use-these-placeholder-values.md
|
|
|
|
|
for-this-example-we-use-a-fake-weather-tool-for-demonstration-purposes.md
|
|
|
|
|
frontend.md
|
|
|
|
|
full-restart-stop-build-backend-start.md
|
|
|
|
|
full-restart-stop-build-start-default.md
|
|
|
|
|
g-eval.md
|
|
|
|
|
gateway.md
|
|
|
|
|
generate-3-candidates-per-evaluation-select-best-2.md
|
|
|
|
|
generate-3-candidates-per-evaluation-select-best.md
|
|
|
|
|
generate-a-user-message-based-on-a-couple-of-back-and-forth-turns.md
|
|
|
|
|
generate-a-user-message-that-will-start-the-conversation.md
|
|
|
|
|
generate-a-video.md
|
|
|
|
|
generate-synthetic-version.md
|
|
|
|
|
generate-the-dataset.md
|
|
|
|
|
generate-videos.md
|
|
|
|
|
gepa-example-optimizing-an-agent-with-function-calling.md
|
|
|
|
|
gepa-optimizer.md
|
|
|
|
|
gepa-optimizes-the-agents-prompt-not-the-tools-themselves.md
|
|
|
|
|
get-a-specific-trace-by-id.md
|
|
|
|
|
get-a-tracer.md
|
|
|
|
|
get-alert-by-id.md
|
|
|
|
|
get-all-dataset-export-jobs.md
|
|
|
|
|
get-annotation-queue-by-id.md
|
|
|
|
|
get-automation-rule-evaluator-by-id.md
|
|
|
|
|
get-automation-rule-evaluator-logs-by-id.md
|
|
|
|
|
get-cost-daily-data.md
|
|
|
|
|
get-costs-summary.md
|
|
|
|
|
get-dashboard-by-id.md
|
|
|
|
|
get-dataset-by-id.md
|
|
|
|
|
get-dataset-by-name.md
|
|
|
|
|
get-dataset-export-job-status.md
|
|
|
|
|
get-dataset-item-by-id.md
|
|
|
|
|
get-dataset-items-output-columns.md
|
|
|
|
|
get-dataset-items.md
|
|
|
|
|
get-datasets-information-for-bi-events.md
|
|
|
|
|
get-experiment-by-id.md
|
|
|
|
|
get-experiment-item-by-id.md
|
|
|
|
|
get-experiment-items-stats-for-dataset.md
|
|
|
|
|
get-experiments-information-for-bi-events.md
|
|
|
|
|
get-feedback-definition-by-id.md
|
|
|
|
|
get-list-of-attachments.md
|
|
|
|
|
get-llm-providers-apikey-by-id.md
|
|
|
|
|
get-metric-daily-data.md
|
|
|
|
|
get-metrics-summary.md
|
|
|
|
|
get-optimization-by-id.md
|
|
|
|
|
get-project-by-id.md
|
|
|
|
|
get-project-metrics.md
|
|
|
|
|
get-project-stats.md
|
|
|
|
|
get-prompt-by-id.md
|
|
|
|
|
get-prompt-from-the-prompt-library.md
|
|
|
|
|
get-prompt-version-by-id.md
|
|
|
|
|
get-prompt-versions.md
|
|
|
|
|
get-prompts.md
|
|
|
|
|
get-service-toggles.md
|
|
|
|
|
get-span-by-id.md
|
|
|
|
|
get-span-comment.md
|
|
|
|
|
get-span-stats.md
|
|
|
|
|
get-spans-by-project-name-or-project-id-and-optionally-by-trace-id-andor-type.md
|
|
|
|
|
get-spans-count-on-previous-day-for-all-available-workspaces.md
|
|
|
|
|
get-spans-information-for-bi-events.md
|
|
|
|
|
get-started-with-opentelemetry.md
|
|
|
|
|
get-studio-optimization-logs.md
|
|
|
|
|
get-the-current-possibly-overridden-prompt.md
|
|
|
|
|
get-the-dataset-2.md
|
|
|
|
|
get-the-dataset.md
|
|
|
|
|
get-the-original-default-before-any-overrides.md
|
|
|
|
|
get-the-trace-id-from-the-pipeline-run-response.md
|
|
|
|
|
get-thread-comment.md
|
|
|
|
|
get-trace-by-id.md
|
|
|
|
|
get-trace-comment.md
|
|
|
|
|
get-trace-stats.md
|
|
|
|
|
get-trace-thread-stats.md
|
|
|
|
|
get-trace-thread.md
|
|
|
|
|
get-trace-threads.md
|
|
|
|
|
get-traces-by-project-name-or-project-id.md
|
|
|
|
|
get-traces-count-on-previous-day-for-all-available-workspaces.md
|
|
|
|
|
get-traces-information-for-bi-events.md
|
|
|
|
|
get-webhook-payload-examples.md
|
|
|
|
|
get-welcome-wizard-tracking-status.md
|
|
|
|
|
get-workspace-configuration.md
|
|
|
|
|
gets-the-api-key-from-environment-variable-azure-openai-api-key.md
|
|
|
|
|
getting-started.md
|
|
|
|
|
getting-the-content-of-the-logged-traces.md
|
|
|
|
|
good-analyzing-execution-patterns.md
|
|
|
|
|
google.md
|
|
|
|
|
gretel-configuration.md
|
|
|
|
|
guardrails.md
|
|
|
|
|
hallucination.md
|
|
|
|
|
heuristic-metrics.md
|
|
|
|
|
home.md
|
|
|
|
|
hosting-1-package.md
|
|
|
|
|
how-it-works-2.md
|
|
|
|
|
how-it-works.md
|
|
|
|
|
hrpo-hierarchical-reflective-prompt-optimizer.md
|
|
|
|
|
hugging-face-configuration-optional-for-private-datasets.md
|
|
|
|
|
if-running-locally.md
|
|
|
|
|
if-running-on-opik-cloud.md
|
|
|
|
|
import-datasets-from-default-directory-opik-exports.md
|
|
|
|
|
import-datasets-to-another-workspace-uses-default-opik-exports-directory.md
|
|
|
|
|
import-experiments-automatically-recreates-experiments.md
|
|
|
|
|
import-experiments-from-default-directory-automatically-recreates-experiments.md
|
|
|
|
|
import-experiments-matching-name-pattern.md
|
|
|
|
|
import-from-custom-path.md
|
|
|
|
|
import-otlp-exporter.md
|
|
|
|
|
import-projects-from-default-directory.md
|
|
|
|
|
import-prompts-from-default-directory.md
|
|
|
|
|
import-prompts-to-another-workspace.md
|
|
|
|
|
import-smolagents-instrumentation.md
|
|
|
|
|
import-telemetry-components.md
|
|
|
|
|
import-the-required-dependencies.md
|
|
|
|
|
import-to-new-workspace.md
|
|
|
|
|
import-with-debug-output.md
|
|
|
|
|
import-with-name-pattern-matching-2.md
|
|
|
|
|
import-with-name-pattern-matching.md
|
|
|
|
|
importexport-by-command-line.md
|
|
|
|
|
in-memory-storage-use-a-database-in-production.md
|
|
|
|
|
in-your-cicd-pipeline.md
|
|
|
|
|
in-your-service-that-receives-distributed-trace-headers.md
|
|
|
|
|
in-your-webhook-handler.md
|
|
|
|
|
infrastructure-backend-services.md
|
|
|
|
|
infrastructure-only-mysql-redis-clickhouse-zookeeper-minio.md
|
|
|
|
|
initialize-and-track-the-bedrock-client-2.md
|
|
|
|
|
initialize-and-track-the-bedrock-client-3.md
|
|
|
|
|
initialize-and-track-the-bedrock-client.md
|
|
|
|
|
initialize-data-designer.md
|
|
|
|
|
initialize-litellm-with-openai-gpt-4o-2.md
|
|
|
|
|
initialize-litellm-with-openai-gpt-4o.md
|
|
|
|
|
initialize-opentelemetry-with-the-http-exporter.md
|
|
|
|
|
initialize-opik-client.md
|
|
|
|
|
initialize-optimizer-2.md
|
|
|
|
|
initialize-optimizer-3.md
|
|
|
|
|
initialize-optimizer.md
|
|
|
|
|
initialize-the-converter.md
|
|
|
|
|
initialize-the-evaluation-metrics.md
|
|
|
|
|
initialize-the-hallucination-metric-with-the-custom-model.md
|
|
|
|
|
initialize-the-language-model.md
|
|
|
|
|
initialize-the-metric-with-your-preferred-judge-model.md
|
|
|
|
|
initialize-the-openai-client-with-byteplus-base-url.md
|
|
|
|
|
initialize-the-openai-client-with-openrouter-base-url.md
|
|
|
|
|
initialize-the-optimizer.md
|
|
|
|
|
initialize-the-ragas-metric-2.md
|
|
|
|
|
initialize-the-ragas-metric.md
|
|
|
|
|
initialize-the-state.md
|
|
|
|
|
initialize-the-trace-provider.md
|
|
|
|
|
initialize-the-tracer.md
|
|
|
|
|
initialize-your-custom-model.md
|
|
|
|
|
initialize-your-metrics.md
|
|
|
|
|
insert-items-into-dataset-2.md
|
|
|
|
|
insert-items-into-dataset.md
|
|
|
|
|
insert-the-data.md
|
|
|
|
|
insert-the-dataset-items.md
|
|
|
|
|
install-globally.md
|
|
|
|
|
installation.md
|
|
|
|
|
instrument-smolagents.md
|
|
|
|
|
instrument-the-agent-with-a-single-function-call-this-is-the-recommended-approac-2.md
|
|
|
|
|
instrument-the-agent-with-a-single-function-call-this-is-the-recommended-approac.md
|
|
|
|
|
instrument-the-agent-with-track-adk-agent-recursive.md
|
|
|
|
|
instrument-your-framework.md
|
|
|
|
|
invoke-the-fine-tuned-model.md
|
|
|
|
|
it-captures-the-agents-actual-tool-calls-from-its-outputs.md
|
|
|
|
|
it-logs-the-evaluation-results-to-opik-under-the-specified-experiment-name-agent.md
|
|
|
|
|
it-loops-over-each-dataset-item-and-applies-the-evaluation-task-function-to-gene.md
|
|
|
|
|
it-packages-the-original-input-the-agents-outputs-the-detected-tool-calls-and-th.md
|
|
|
|
|
it-sends-the-input-as-a-message-to-the-agent-agent-executor.md
|
|
|
|
|
it-then-applies-the-custom-toolselectionquality-metric-or-any-provided-metrics-t.md
|
|
|
|
|
january-13-2025.md
|
|
|
|
|
january-13-2026.md
|
|
|
|
|
january-20-2025.md
|
|
|
|
|
january-27-2025.md
|
|
|
|
|
january-27-2026.md
|
|
|
|
|
january-6-2025.md
|
|
|
|
|
job-management.md
|
|
|
|
|
july-18-2025.md
|
|
|
|
|
july-4-2025.md
|
|
|
|
|
june-20-2025.md
|
|
|
|
|
june-6-2025.md
|
|
|
|
|
keyerror-unknown-prompt-keys-reasoing-system.md
|
|
|
|
|
kill-stuck-backend-process.md
|
|
|
|
|
kill-stuck-frontend-process.md
|
|
|
|
|
known-issues.md
|
|
|
|
|
kubernetes-2.md
|
|
|
|
|
kubernetes-3.md
|
|
|
|
|
kubernetes-deployment.md
|
|
|
|
|
kubernetes.md
|
|
|
|
|
kuberneteshelm.md
|
|
|
|
|
langchain-operations-will-be-attached-to-the-existing-distributed-trace.md
|
|
|
|
|
large-csv-uploads.md
|
|
|
|
|
layer-1-basic-pii-patterns.md
|
|
|
|
|
layer-2-compliance-specific-anonymization.md
|
|
|
|
|
layer-3-custom-business-logic.md
|
|
|
|
|
lint-frontend.md
|
|
|
|
|
list-all-datasets-with-pagination.md
|
|
|
|
|
list-available-backups.md
|
|
|
|
|
list-available-ollama-models.md
|
|
|
|
|
list-dataset-versions.md
|
|
|
|
|
list-tables-example-path-adjust-for-your-database-name.md
|
|
|
|
|
list-tables-in-zookeeper.md
|
|
|
|
|
llm-juries-judge.md
|
|
|
|
|
llm-juries.md
|
|
|
|
|
llm-provider-api-keys-if-needed.md
|
|
|
|
|
llms-full.txt
|
|
|
|
|
llms.txt
|
|
|
|
|
load-a-dataset-from-hugging-face.md
|
|
|
|
|
load-and-extract-text-from-pdfs.md
|
|
|
|
|
load-common-crawl-dataset.md
|
|
|
|
|
load-glue-sst-2-dataset.md
|
|
|
|
|
load-squad-dataset.md
|
|
|
|
|
local-deployment.md
|
|
|
|
|
local-development-setup.md
|
|
|
|
|
log-agent-graphs.md
|
|
|
|
|
log-all-traces-made-to-with-the-openai-client-to-opik.md
|
|
|
|
|
log-attachment-with-file-path.md
|
|
|
|
|
log-attachment-with-raw-bytes.md
|
|
|
|
|
log-conversations.md
|
|
|
|
|
log-distributed-traces.md
|
|
|
|
|
log-media-attachments.md
|
|
|
|
|
log-the-feedback-score.md
|
|
|
|
|
log-traces-2.md
|
|
|
|
|
log-traces.md
|
|
|
|
|
log-user-feedback.md
|
|
|
|
|
logging-configuration-see-debug-mode-and-logging-section-below.md
|
|
|
|
|
make-a-chat-completion-call.md
|
|
|
|
|
make-a-chat-completion-request-2.md
|
|
|
|
|
make-a-chat-completion-request-3.md
|
|
|
|
|
make-a-chat-completion-request-4.md
|
|
|
|
|
make-a-chat-completion-request-5.md
|
|
|
|
|
make-a-chat-completion-request.md
|
|
|
|
|
make-sure-to-wrap-the-openai-client-to-enable-opik-tracing.md
|
|
|
|
|
manage-datasets.md
|
|
|
|
|
manage-services.md
|
|
|
|
|
manually-evaluate-spans.md
|
|
|
|
|
manually-evaluate-threads.md
|
|
|
|
|
manually-evaluate-traces.md
|
|
|
|
|
manually-logging-experiments.md
|
|
|
|
|
march-10-2025.md
|
|
|
|
|
march-17-2025.md
|
|
|
|
|
march-24-2025.md
|
|
|
|
|
march-3-2025.md
|
|
|
|
|
march-31-2025.md
|
|
|
|
|
mark-dataset-export-job-as-viewed.md
|
|
|
|
|
may-23-2025.md
|
|
|
|
|
may-5-2025.md
|
|
|
|
|
mcp-tools-are-configured-through-mcpjson-manifests.md
|
|
|
|
|
meaning-match-2.md
|
|
|
|
|
meaning-match.md
|
|
|
|
|
metaprompt-optimizer.md
|
|
|
|
|
method-to-log-data-to-opik.md
|
|
|
|
|
metric-that-needs-task-span-2.md
|
|
|
|
|
metric-that-needs-task-span.md
|
|
|
|
|
migrating-from-bitnami-charts-and-images-2.md
|
|
|
|
|
migrating-from-bitnami-charts-and-images.md
|
|
|
|
|
mix-of-dictionary-tuple-and-function-rules.md
|
|
|
|
|
mix-regular-and-task-span-metrics.md
|
|
|
|
|
models.md
|
|
|
|
|
moderation.md
|
|
|
|
|
more-creative-responses.md
|
|
|
|
|
more-factual-responses.md
|
|
|
|
|
multimodal-agent-optimization-tutorial.md
|
|
|
|
|
multiple-completions-n-parameter.md
|
|
|
|
|
multiple-references-2.md
|
|
|
|
|
multiple-references.md
|
|
|
|
|
navigate-to-the-opikdeploymentdocker-compose-directory.md
|
|
|
|
|
negative-sentiment-example.md
|
|
|
|
|
next-steps-set-expectations.md
|
|
|
|
|
no-authentication-headers-required-for-local-deployments.md
|
|
|
|
|
no-callbacks-needed-here-either.md
|
|
|
|
|
no-code-llm-evaluation-workflow.md
|
|
|
|
|
note-check-same-threadfalse-is-ok-as-the-implementation-uses-a-lock.md
|
|
|
|
|
november-11-2024.md
|
|
|
|
|
november-18-2024.md
|
|
|
|
|
november-18-2025.md
|
|
|
|
|
november-25-2024.md
|
|
|
|
|
november-4-2024.md
|
|
|
|
|
november-4-2025.md
|
|
|
|
|
novita-ai-configuration.md
|
|
|
|
|
now-all-invocations-are-automatically-tracked.md
|
|
|
|
|
now-all-traced-functions-will-automatically-anonymize-pii.md
|
|
|
|
|
now-use-smolagents-as-usual.md
|
|
|
|
|
now-we-can-define-and-call-the-agent.md
|
|
|
|
|
now-you-can-use-any-of-the-available-client-methods.md
|
|
|
|
|
observability-for-ag2-with-opik.md
|
|
|
|
|
observability-for-agno-with-opik.md
|
|
|
|
|
observability-for-aisuite-with-opik.md
|
|
|
|
|
observability-for-anannas-ai-with-opik.md
|
|
|
|
|
observability-for-anthropic-with-opik.md
|
|
|
|
|
observability-for-autogen-with-opik.md
|
|
|
|
|
observability-for-aws-bedrock-with-opik.md
|
|
|
|
|
observability-for-beeai-python-with-opik.md
|
|
|
|
|
observability-for-beeai-typescript-with-opik.md
|
|
|
|
|
observability-for-byteplus-with-opik.md
|
|
|
|
|
observability-for-cloudflare-workers-ai-with-opik.md
|
|
|
|
|
observability-for-cohere-with-opik.md
|
|
|
|
|
observability-for-crewai-with-opik.md
|
|
|
|
|
observability-for-cursor-with-opik.md
|
|
|
|
|
observability-for-deepseek-with-opik.md
|
|
|
|
|
observability-for-dify-with-opik.md
|
|
|
|
|
observability-for-dspy-with-opik.md
|
|
|
|
|
observability-for-fireworks-ai-with-opik.md
|
|
|
|
|
observability-for-flowise-with-opik.md
|
|
|
|
|
observability-for-google-agent-development-kit-python-with-opik.md
|
|
|
|
|
observability-for-google-gemini-python-with-opik.md
|
|
|
|
|
observability-for-google-gemini-typescript-with-opik.md
|
|
|
|
|
observability-for-gretel-with-opik.md
|
|
|
|
|
observability-for-groq-with-opik.md
|
|
|
|
|
observability-for-harbor-with-opik.md
|
|
|
|
|
observability-for-haystack-with-opik.md
|
|
|
|
|
observability-for-helicone-with-opik.md
|
|
|
|
|
observability-for-hugging-face-datasets-with-opik.md
|
|
|
|
|
observability-for-ibm-watsonx-with-opik.md
|
|
|
|
|
observability-for-kong-ai-gateway-with-opik.md
|
|
|
|
|
observability-for-langchain-javascript-with-opik.md
|
|
|
|
|
observability-for-langchain-python-with-opik.md
|
|
|
|
|
observability-for-langflow-with-opik.md
|
|
|
|
|
observability-for-langgraph-with-opik.md
|
|
|
|
|
observability-for-litellm-with-opik.md
|
|
|
|
|
observability-for-livekit-with-opik.md
|
|
|
|
|
observability-for-llamaindex-with-opik.md
|
|
|
|
|
observability-for-mastra-with-opik.md
|
|
|
|
|
observability-for-microsoft-agent-framework-net-with-opik.md
|
|
|
|
|
observability-for-microsoft-agent-framework-python-with-opik.md
|
|
|
|
|
observability-for-mistral-ai-with-opik.md
|
|
|
|
|
observability-for-n8n-with-opik.md
|
|
|
|
|
observability-for-novita-ai-with-opik.md
|
|
|
|
|
observability-for-ollama-with-opik.md
|
|
|
|
|
observability-for-openai-agents-with-opik.md
|
|
|
|
|
observability-for-openai-python-with-opik.md
|
|
|
|
|
observability-for-openai-typescript-with-opik.md
|
|
|
|
|
observability-for-openrouter-with-opik.md
|
|
|
|
|
observability-for-openwebui-with-opik.md
|
|
|
|
|
observability-for-opik-llm-gateway-with-opik.md
|
|
|
|
|
observability-for-pipecat-with-opik.md
|
|
|
|
|
observability-for-portkey-with-opik.md
|
|
|
|
|
observability-for-predibase-with-opik.md
|
|
|
|
|
observability-for-pydantic-ai-with-opik.md
|
|
|
|
|
observability-for-semantic-kernel-python-with-opik.md
|
|
|
|
|
observability-for-smolagents-with-opik.md
|
|
|
|
|
observability-for-spring-ai-java-with-opik.md
|
|
|
|
|
observability-for-strands-agents-with-opik.md
|
|
|
|
|
observability-for-together-ai-with-opik.md
|
|
|
|
|
observability-for-truefoundry-with-opik.md
|
|
|
|
|
observability-for-vercel-ai-gateway-with-opik.md
|
|
|
|
|
observability-for-vercel-ai-sdk-with-opik.md
|
|
|
|
|
observability-for-voltagent-with-opik.md
|
|
|
|
|
observability-for-xai-grok-with-opik.md
|
|
|
|
|
october-14-2024.md
|
|
|
|
|
october-18-2024.md
|
|
|
|
|
october-21-2024.md
|
|
|
|
|
october-21-2025.md
|
|
|
|
|
october-3-2025.md
|
|
|
|
|
october-7-2024.md
|
|
|
|
|
on-windows-2.md
|
|
|
|
|
on-windows-3.md
|
|
|
|
|
on-windows.md
|
|
|
|
|
online-evaluation-rules-2.md
|
|
|
|
|
online-evaluation-rules.md
|
|
|
|
|
only-trace-specific-nodes.md
|
|
|
|
|
open-trace-thread.md
|
|
|
|
|
opentelemetry-3-packages.md
|
|
|
|
|
opentelemetry-configrb.md
|
|
|
|
|
opentelemetry-python-sdk.md
|
|
|
|
|
opentelemetry-ruby-sdk.md
|
|
|
|
|
opentelemetry.md
|
|
|
|
|
opik-agent-optimizer-api-reference.md
|
|
|
|
|
opik-agent-optimizer-core-concepts.md
|
|
|
|
|
opik-assist-beta.md
|
|
|
|
|
opik-bounty-program.md
|
|
|
|
|
opik-configuration-2.md
|
|
|
|
|
opik-configuration-3.md
|
|
|
|
|
opik-configuration-4.md
|
|
|
|
|
opik-configuration-5.md
|
|
|
|
|
opik-configuration-6.md
|
|
|
|
|
opik-configuration-7.md
|
|
|
|
|
opik-configuration.md
|
|
|
|
|
opik-optimizer.md
|
|
|
|
|
opik-overview.md
|
|
|
|
|
opik-query-language-oql.md
|
|
|
|
|
opik-ts-interactive-setup-tool.md
|
|
|
|
|
opik-typescript-sdk.md
|
|
|
|
|
opiks-mcp-server.md
|
|
|
|
|
optimization-algorithms-overview.md
|
|
|
|
|
optimization-studio.md
|
|
|
|
|
optimize-agents.md
|
|
|
|
|
optimize-each-trial-evaluates-3-candidates-picks-best.md
|
|
|
|
|
optimize-more-parameters-including-model-selection.md
|
|
|
|
|
optimize-multimodal-prompts.md
|
|
|
|
|
optimize-prompts.md
|
|
|
|
|
optimizer-benchmarks.md
|
|
|
|
|
optimizer-frequently-asked-questions.md
|
|
|
|
|
optimizer-introduction-cookbook.md
|
|
|
|
|
optimizer-model-this-is-the-model-that-improves-your-prompt.md
|
|
|
|
|
option-1-include-sensitive-data-prompts-and-completions.md
|
|
|
|
|
option-2-hide-sensitive-data-prompts-and-completions.md
|
|
|
|
|
optional-can-also-be-passed-as-params-to-completion-or-embedding.md
|
|
|
|
|
optional-headers-for-openrouter-leaderboard.md
|
|
|
|
|
or-get-real-credentials-from-httpscloudlivekitio.md
|
|
|
|
|
or-manually-remove-containers-and-volumes.md
|
|
|
|
|
or-set-environment-variable.md
|
|
|
|
|
or-via-http.md
|
|
|
|
|
or-with-optional-parameters.md
|
|
|
|
|
original-generate-num-prompts-variations-of-the-prompt.md
|
|
|
|
|
osenvironsemantickernel-experimental-genai-enable-otel-diagnostics-true.md
|
|
|
|
|
osenvironwatsonx-deployment-space-id-id-of-your-deployment-space-to-use-deployed.md
|
|
|
|
|
osenvironwatsonx-project-id-project-id-of-your-watsonx-instance.md
|
|
|
|
|
other-gems.md
|
|
|
|
|
overall-chain.md
|
|
|
|
|
overview-2.md
|
|
|
|
|
overview-3.md
|
|
|
|
|
overview-4.md
|
|
|
|
|
overview-5.md
|
|
|
|
|
overview-6.md
|
|
|
|
|
overview-7.md
|
|
|
|
|
overview-8.md
|
|
|
|
|
overview-9.md
|
|
|
|
|
overview.md
|
|
|
|
|
parameter-optimizer-bayesian-parameter-tuning.md
|
|
|
|
|
partially-update-dataset-item-by-id.md
|
|
|
|
|
pass-intermediate-results-to-subsequent-prompts.md
|
|
|
|
|
pass-the-opiktracer-callback-to-each-invocation.md
|
|
|
|
|
pass-thread-id-via-opik-args.md
|
|
|
|
|
patch-the-anthropic-client-for-instructor.md
|
|
|
|
|
patch-the-genai-client-for-instructor.md
|
|
|
|
|
patch-the-openai-client-for-instructor.md
|
|
|
|
|
pii-in-prompts-will-be-automatically-anonymized-in-traces.md
|
|
|
|
|
platform-architecture.md
|
|
|
|
|
port-forward-to-access-the-backup-server.md
|
|
|
|
|
pre-compile-regex-for-better-performance.md
|
|
|
|
|
prepare-dataset-2.md
|
|
|
|
|
prepare-dataset-3.md
|
|
|
|
|
prepare-dataset.md
|
|
|
|
|
prerequisites.md
|
|
|
|
|
print-the-assistants-reply-2.md
|
|
|
|
|
print-the-assistants-reply-3.md
|
|
|
|
|
print-the-assistants-reply-4.md
|
|
|
|
|
print-the-assistants-reply-5.md
|
|
|
|
|
print-the-assistants-reply.md
|
|
|
|
|
production-monitoring.md
|
|
|
|
|
prompt-generator-and-improver.md
|
|
|
|
|
prompt-management-2.md
|
|
|
|
|
prompt-management.md
|
|
|
|
|
prompt-playground-2.md
|
|
|
|
|
prompt-playground.md
|
|
|
|
|
prompt-uncertainty-2.md
|
|
|
|
|
prompt-uncertainty.md
|
|
|
|
|
prompts.md
|
|
|
|
|
pytest-integration-2.md
|
|
|
|
|
pytest-integration.md
|
|
|
|
|
python-sdk.md
|
|
|
|
|
quick-start.md
|
|
|
|
|
quickstart-2.md
|
|
|
|
|
quickstart-notebook-summarization.md
|
|
|
|
|
quickstart-notebook.md
|
|
|
|
|
quickstart.md
|
|
|
|
|
re-running-an-existing-experiment.md
|
|
|
|
|
read-all-trace-csv-files-and-combine-them.md
|
|
|
|
|
rebuild-specific-service.md
|
|
|
|
|
receive-protobuf-traces.md
|
|
|
|
|
record-experiment-items-in-bulk.md
|
|
|
|
|
reduce-console-output-to-warnings-and-errors-only.md
|
|
|
|
|
reformat-the-dataset-to-match-the-schema-expected-by-the-ragas-evaluate-function-2.md
|
|
|
|
|
reformat-the-dataset-to-match-the-schema-expected-by-the-ragas-evaluate-function.md
|
|
|
|
|
register-globally.md
|
|
|
|
|
register-the-custom-anonymizer.md
|
|
|
|
|
register-the-field-aware-anonymizer.md
|
|
|
|
|
register-the-presidio-based-anonymizer-globally.md
|
|
|
|
|
regular-metric-without-task-span.md
|
|
|
|
|
remove-a-specific-table-from-zookeeper.md
|
|
|
|
|
remove-hooks.md
|
|
|
|
|
remove-items-from-annotation-queue.md
|
|
|
|
|
remove-opik-docker-volumes-warning-data-loss-removes-opik-databases.md
|
|
|
|
|
replace-my-experiment-with-the-name-of-your-experiment-which-can-be-found-in-the.md
|
|
|
|
|
required-either-one-of-the-following.md
|
|
|
|
|
rest-api-client.md
|
|
|
|
|
restart-a-specific-docker-service.md
|
|
|
|
|
restart.md
|
|
|
|
|
restore-backup.md
|
|
|
|
|
restore-dataset-to-a-previous-version.md
|
|
|
|
|
restore-from-s3-backup.md
|
|
|
|
|
restore-prompt-version.md
|
|
|
|
|
result-is-the-optimizationresult-returned-by-your-optimizer-call.md
|
|
|
|
|
retrieve-and-print-the-aggregated-scores-statistics-mean-min-max-std-per-metric.md
|
|
|
|
|
retrieve-project.md
|
|
|
|
|
retrieve-prompt-version.md
|
|
|
|
|
returns-a-parsed-pydantic-object-not-raw-text.md
|
|
|
|
|
returns-estimated-cost-in-usd-or-none-for-unsupported-models-2.md
|
|
|
|
|
returns-estimated-cost-in-usd-or-none-for-unsupported-models.md
|
|
|
|
|
returns-list-of-message-dicts-role-system-content.md
|
|
|
|
|
reuse-the-optimized-prompt-from-the-first-stage.md
|
|
|
|
|
review-chain.md
|
|
|
|
|
roadmap.md
|
|
|
|
|
route-to-different-handlers-based-on-environment.md
|
|
|
|
|
run-a-benchmark-with-opik-tracking.md
|
|
|
|
|
run-a-job-alias-for-jobs-start.md
|
|
|
|
|
run-evaluation.md
|
|
|
|
|
run-migrations-only.md
|
|
|
|
|
run-optimization-2.md
|
|
|
|
|
run-optimization-3.md
|
|
|
|
|
run-optimization-4.md
|
|
|
|
|
run-optimization.md
|
|
|
|
|
run-swe-bench-evaluation-with-tracking.md
|
|
|
|
|
run-the-agent-2.md
|
|
|
|
|
run-the-agent-and-stream-the-messages-to-the-console.md
|
|
|
|
|
run-the-agent.md
|
|
|
|
|
run-the-chain-with-opik-tracing.md
|
|
|
|
|
run-the-crew.md
|
|
|
|
|
run-the-evaluation-2.md
|
|
|
|
|
run-the-evaluation-3.md
|
|
|
|
|
run-the-evaluation-4.md
|
|
|
|
|
run-the-evaluation-5.md
|
|
|
|
|
run-the-evaluation-6.md
|
|
|
|
|
run-the-evaluation.md
|
|
|
|
|
run-the-example.md
|
|
|
|
|
run-the-threads-evaluation.md
|
|
|
|
|
run-with-more-trials-and-custom-optuna-sampler.md
|
|
|
|
|
run-zookeeper-client-commands.md
|
|
|
|
|
sampling-controls.md
|
|
|
|
|
scaling-opik-2.md
|
|
|
|
|
scaling-opik.md
|
|
|
|
|
sdk-configuration-2.md
|
|
|
|
|
sdk-configuration.md
|
|
|
|
|
search-spans.md
|
|
|
|
|
search-trace-threads.md
|
|
|
|
|
search-traces-with-advanced-filters.md
|
|
|
|
|
search-traces.md
|
|
|
|
|
security-considerations.md
|
|
|
|
|
see-scriptsarchivelitellm-metaprompt-context7-mcp-examplepy-for-working-examples.md
|
|
|
|
|
september-30-2024.md
|
|
|
|
|
september-5-2025.md
|
|
|
|
|
set-project-name-for-better-organization-2.md
|
|
|
|
|
set-project-name-for-better-organization-3.md
|
|
|
|
|
set-project-name-for-better-organization.md
|
|
|
|
|
set-project-name-for-organization-2.md
|
|
|
|
|
set-project-name-for-organization-3.md
|
|
|
|
|
set-project-name-for-organization.md
|
|
|
|
|
set-project-name-via-environment-variable-2.md
|
|
|
|
|
set-project-name-via-environment-variable-3.md
|
|
|
|
|
set-project-name-via-environment-variable-4.md
|
|
|
|
|
set-project-name-via-environment-variable.md
|
|
|
|
|
set-project-name.md
|
|
|
|
|
set-the-tracer-provider.md
|
|
|
|
|
set-up-anonymization.md
|
|
|
|
|
set-up-api-keys.md
|
|
|
|
|
set-up-evaluation.md
|
|
|
|
|
set-up-langchain-with-opik-tracing.md
|
|
|
|
|
set-up-multi-layer-anonymization.md
|
|
|
|
|
set-up-the-otlp-http-exporter.md
|
|
|
|
|
set-up-the-tracer-provider-with-span-processor.md
|
|
|
|
|
set-up-the-tracer-provider.md
|
|
|
|
|
set-your-opik-api-key-get-one-free-at-httpswwwcometcomsignup.md
|
|
|
|
|
show-recent-logs-last-20-lines.md
|
|
|
|
|
simple-dict-override.md
|
|
|
|
|
single-reference-2.md
|
|
|
|
|
single-reference.md
|
|
|
|
|
single-trial.md
|
|
|
|
|
specific-commands.md
|
|
|
|
|
start-dataset-csv-export.md
|
|
|
|
|
start-full-opik-platform-equivalent-to-opiksh.md
|
|
|
|
|
start-infrastructure-backend-services-equivalent-to-opiksh-backend.md
|
|
|
|
|
start-instrumenting-agno.md
|
|
|
|
|
start-multipart-attachment-upload.md
|
|
|
|
|
start-only-infrastructure-services-equivalent-to-opiksh-infra.md
|
|
|
|
|
start-only-infrastructure-services.md
|
|
|
|
|
start-without-rebuilding-faster-if-no-dependency-changes.md
|
|
|
|
|
start-without-rebuilding-if-no-code-changes.md
|
|
|
|
|
start-without-rebuilding.md
|
|
|
|
|
statemessagesappendhumanmessagecontentwhat-is-my-name.md
|
|
|
|
|
stop-all-services.md
|
|
|
|
|
stop-infrastructure.md
|
|
|
|
|
stop-services.md
|
|
|
|
|
store-llm-providers-apikey.md
|
|
|
|
|
stream-dataset-items.md
|
|
|
|
|
stream-experiment-items.md
|
|
|
|
|
stream-experiments.md
|
|
|
|
|
structured-output-tracking-for-instructor-with-opik.md
|
|
|
|
|
submit-welcome-wizard.md
|
|
|
|
|
summarization-coherence-judge.md
|
|
|
|
|
summarization-coherence.md
|
|
|
|
|
summarization-consistency-judge.md
|
|
|
|
|
summarization-consistency.md
|
|
|
|
|
sync-from-staging-to-production.md
|
|
|
|
|
synchronous-execution-tracked-functions-work-automatically.md
|
|
|
|
|
synopsis-chain.md
|
|
|
|
|
synthetic-data-optimizer-cookbook.md
|
|
|
|
|
task-span-metrics-2.md
|
|
|
|
|
task-span-metrics.md
|
|
|
|
|
test-alert-webhook.md
|
|
|
|
|
test-api-connectivity.md
|
|
|
|
|
test-connection-to-ollama-instance.md
|
|
|
|
|
test-s3-connectivity.md
|
|
|
|
|
test-the-chain.md
|
|
|
|
|
test-the-model-with-opik-tracing.md
|
|
|
|
|
test-with-a-different-input-still-tracked-automatically.md
|
|
|
|
|
test-with-nested-data.md
|
|
|
|
|
test-with-sample-data.md
|
|
|
|
|
the-chatcompletionclient-interface.md
|
|
|
|
|
the-distributed-headers-dict-can-be-obtained-in-the-parent-service-via-opik-cont.md
|
|
|
|
|
the-graph-visualization-is-automatically-extracted-by-track-langgraph-2.md
|
|
|
|
|
the-graph-visualization-is-automatically-extracted-by-track-langgraph.md
|
|
|
|
|
the-metaprompt-optimizer-can-optimize-mcp-tool-descriptions-and-usage.md
|
|
|
|
|
the-opiktrack-decorators-in-your-tools-will-automatically-create-child-spans.md
|
|
|
|
|
the-otel-endpoint-configuration.md
|
|
|
|
|
this-allows-tracking-comparing-and-analyzing-your-agents-tool-selection-quality-.md
|
|
|
|
|
this-automatically-adds-callbacks-to-the-coordinator-and-all-sub-agents.md
|
|
|
|
|
this-function-defines-how-each-item-in-the-dataset-will-be-evaluated.md
|
|
|
|
|
this-is-the-custom-metric-we-have-defined.md
|
|
|
|
|
this-is-the-dataset-with-the-examples-of-good-tool-selection.md
|
|
|
|
|
this-must-be-done-before-any-other-telemetry-calls.md
|
|
|
|
|
this-part-would-be-custom-for-your-use-case-and-is-only-here-for-example.md
|
|
|
|
|
this-structured-output-is-what-the-evaluation-platform-will-use-to-compare-expec.md
|
|
|
|
|
this-will-raise-keyerror-reasoing-system-is-misspelled.md
|
|
|
|
|
time-specialist-agent-no-opik-callbacks-needed.md
|
|
|
|
|
to-ensure-thread-safety.md
|
|
|
|
|
to.md
|
|
|
|
|
token-usage-will-now-be-tracked-in-streaming-responses.md
|
|
|
|
|
tool-optimization-mcp-function-calling.md
|
|
|
|
|
tracing-core-concepts.md
|
|
|
|
|
trajectory-accuracy-2.md
|
|
|
|
|
trajectory-accuracy.md
|
|
|
|
|
travel-specialist-agent-no-opik-callbacks-needed.md
|
|
|
|
|
troubleshooting-2.md
|
|
|
|
|
troubleshooting-3.md
|
|
|
|
|
troubleshooting.md
|
|
|
|
|
tuple-format.md
|
|
|
|
|
type-definition.md
|
|
|
|
|
types-of-anonymizers.md
|
|
|
|
|
types-of-guardrails.md
|
|
|
|
|
typescript-sdk.md
|
|
|
|
|
update-alert.md
|
|
|
|
|
update-annotation-queue.md
|
|
|
|
|
update-automation-rule-evaluator-by-id.md
|
|
|
|
|
update-both-name-and-configuration.md
|
|
|
|
|
update-dashboard.md
|
|
|
|
|
update-dataset-by-id.md
|
|
|
|
|
update-dataset-version.md
|
|
|
|
|
update-experiment-by-id.md
|
|
|
|
|
update-experiment-configuration.md
|
|
|
|
|
update-experiment-name.md
|
|
|
|
|
update-feedback-definition-by-id.md
|
|
|
|
|
update-llm-providers-apikey.md
|
|
|
|
|
update-optimization-by-id.md
|
|
|
|
|
update-project-by-id.md
|
|
|
|
|
update-prompt-versions.md
|
|
|
|
|
update-prompt.md
|
|
|
|
|
update-span-by-id.md
|
|
|
|
|
update-span-comment-by-id.md
|
|
|
|
|
update-thread-comment-by-id.md
|
|
|
|
|
update-thread.md
|
|
|
|
|
update-trace-by-id.md
|
|
|
|
|
update-trace-comment-by-id.md
|
|
|
|
|
upload-a-new-attachment.md
|
|
|
|
|
upload-attachment-to-minio.md
|
|
|
|
|
upload-backup-to-s3.md
|
|
|
|
|
upsert-optimization.md
|
|
|
|
|
upsert-workspace-configuration.md
|
|
|
|
|
usage-examples.md
|
|
|
|
|
use-a-configuration-file.md
|
|
|
|
|
use-a-cost-effective-model-for-prompt-evaluation.md
|
|
|
|
|
use-a-dedicated-quickstart-endpoint-replace-with-your-own-openai-api-key-in-your.md
|
|
|
|
|
use-a-powerful-model-for-optimization-reasoning.md
|
|
|
|
|
use-both-during-optimization.md
|
|
|
|
|
use-force-install-to-bypass-peer-dependency-checks.md
|
|
|
|
|
use-negative-weights-to-minimize-cost-and-duration.md
|
|
|
|
|
use-start-as-current-span-to-track-workflow-execution.md
|
|
|
|
|
use-the-agent.md
|
|
|
|
|
use-the-function.md
|
|
|
|
|
use-the-opik-sdk-as-usual.md
|
|
|
|
|
use-the-ragasmetricwrapper-directly-with-opiks-evaluate-function.md
|
|
|
|
|
use-the-wrapped-client.md
|
|
|
|
|
use-track-adk-agent-recursive-to-instrument-all-agents-at-once.md
|
|
|
|
|
use-url-httplocalhost5173.md
|
|
|
|
|
usefulness.md
|
|
|
|
|
users-default-workspace-name.md
|
|
|
|
|
uses-the-openai-api-key-environment-variable.md
|
|
|
|
|
using-a-chatprompttemplate-with-multimodal-content.md
|
|
|
|
|
using-the-opentelemetry-python-sdk.md
|
|
|
|
|
validation-tracking-for-guardrails-ai-with-opik.md
|
|
|
|
|
valuesyaml.md
|
|
|
|
|
verify-customizations-applied.md
|
|
|
|
|
verify-infrastructure-is-running.md
|
|
|
|
|
version-compatibility.md
|
|
|
|
|
view-all-opik-containers.md
|
|
|
|
|
view-available-options.md
|
|
|
|
|
view-logs-from-docker-services.md
|
|
|
|
|
view-logs.md
|
|
|
|
|
wait-for-completion-and-get-results.md
|
|
|
|
|
we-will-define-the-response-format-so-the-output-has-the-correct-schema-you-can-.md
|
|
|
|
|
we-will-first-create-the-openai-client-and-add-the-track-openai.md
|
|
|
|
|
weather-specialist-agent-no-opik-callbacks-needed.md
|
|
|
|
|
welcome-to-opik-university.md
|
|
|
|
|
what-happens-internally-2.md
|
|
|
|
|
what-happens-internally.md
|
|
|
|
|
wrap-the-client-with-opik-tracking-2.md
|
|
|
|
|
wrap-the-client-with-opik-tracking-3.md
|
|
|
|
|
wrap-the-client-with-opik-tracking-4.md
|
|
|
|
|
wrap-the-client-with-opik-tracking-5.md
|
|
|
|
|
wrap-the-client-with-opik-tracking-6.md
|
|
|
|
|
wrap-the-client-with-opik-tracking-7.md
|
|
|
|
|
wrap-the-client-with-opik-tracking.md
|
|
|
|
|
wrap-the-ragas-metric-with-ragasmetricwrapper-for-opik-integration.md
|
|
|
|
|
xai-configuration.md
|
|
|
|
|
youll-also-need-openai-api-key-for-the-llm-and-tts.md
|
|
|
|
|
your-langgraph-setup.md
|
|
|
|
|
your-opik-code-here-console-will-be-quiet-debug-logs-go-to-file.md
|
|
|
|
|
your-opik-code-here.md
|
|
|
|
|
your-override-should-keep-num-prompts.md
|
|
|
|