Arize-ai/phoenix

phoenix-cli: unknown-command error should suggest upgrading 6 days ago

enhancement good first issue c/dx good-agent-issue c/cli

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT]: Export Experiments for Integration with Other Dashboard 25 days ago

enhancement help wanted backlog c/experiments c/usability

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[js] re-export supress tracing from phoenix-otel 5 months ago

good first issue backlog javascript

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT]: Allow Leveraging of System-Assigned Identity for Azure PostgreSQL Flexible Server 7 months ago

enhancement help wanted user request stale c/auth

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[bug][playground] reasoning content is not displayed when running deepseek via playground 7 months ago

bug help wanted stale c/playground

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[bug][ui] spans table renders wrong cached version (but the header doesn't) when using browser's back/forward button 8 months ago

bug help wanted c/ui stale

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT] improve kustomize overlays 8 months ago

enhancement help wanted backlog c/infra

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT]: [experiments] column selector for experiments table 10 months ago

enhancement good first issue stale c/experiments

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT]: user configured timezone for display in Phoenix web app 10 months ago

enhancement good first issue c/ui

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT] add the ability to collapse and copy the output of a playground run 10 months ago

enhancement good first issue c/ui stale

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT] Modify add_span_processor to support multiple span processors 11 months ago

enhancement help wanted backlog c/traces stale

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT]: Convert Prompts to Langchain format 11 months ago

enhancement help wanted stale c/prompts

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT]: Enable custom-set env vars to come from user-created secrets in the Helm chart 11 months ago

enhancement help wanted

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[BUG]: filtering for numeric values on metadata fails for postgres because CAST to FLOAT fails on records with string values 12 months ago

bug help wanted c/server stale

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[BUG]Filter crashes phoenix 12 months ago

bug help wanted stale priority: medium c/filters

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[BUG] inconsistent size for project cards 12 months ago

bug help wanted c/ui stale

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[enhancement] plumb through metadata for experiment run annotation (e.g. Eval) in the sdk and the ui 12 months ago

enhancement good first issue needs information c/experiments

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT]: Configurable `PHOENIX_DEFAULT_RETENTION_POLICY_DAYS` for Helm deployment about 1 year ago

enhancement help wanted c/helm

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[enhancement][helm] helm support for oidc env vars about 1 year ago

enhancement good first issue help wanted

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

[ENHANCEMENT][TS]: In-memory dataset usage in runExperiment parameters about 1 year ago

AI Summary: Enhance the Arize Phoenix platform's TypeScript client to allow running experiments using in-memory datasets provided as parameters to the `runExperiment` function, eliminating the need for persistent dataset storage. This involves modifying the function to accept a dataset object containing examples directly, rather than a dataset ID.

Complexity: 3/5

enhancement good first issue triage

Arize-ai/phoenix

10.5K

AI Observability & Evaluation

Python

#agents#ai-monitoring#ai-observability#aiengineering#anthropic#datasets#evals#langchain#llamaindex#llm-eval#llm-evaluation#llmops#llms#openai#prompt-engineering#smolagents

Open Issues Need Help