jlewi/foyle

Issues

• Demo: RunMe in a K8s ephemeral pod

  #160 opened 6 hours ago
  0

• Use LLAMA3 On Replicate

  #158 opened 7 days ago
  1

• Set/Learn "interactive" mode and other cell configuration

  #157 opened 7 days ago
  0

• Error learning from example

  #155 opened 7 days ago
  0

• Watch shared location for new/updated examples

  #154 opened 11 days ago
  0

• Support storing examples on S3

  #153 opened 11 days ago
  1

• Datadog integration

  #151 opened 13 days ago
  0

• Example of composability and recipes time ranges and honeycomb queries

  #147 opened 13 days ago
  0

• Easy cloud storage

  #145 opened 11 days ago
  2

• Backfill learning

  #144 opened 18 days ago
  0

• Support for non-bash Runme notebooks cells

  #143 opened 19 days ago
  2

• Make evaluation work with continuous logs analysis

  #140 opened 25 days ago
  1

• Two eval files aren't processed

  #137 opened a month ago
  1

• During Eval Agent trace ids are 00000000000000000000000000000000

  #136 opened a month ago
  2

• Annotate Generate Traces With RAG results

  #135 opened a month ago
  1

• Not learning from block; trace is missing

  #134 opened a month ago
  2

• Eval Results - Have Distance -1 and Normalized Distance of 0

  #132 opened a month ago
  1

• Link Eval Results To Traces

  #131 opened a month ago
  0

• Get Rid Of Non RunMe CodePaths

  #130 opened a month ago
  0

• Build an evaluation dataset as markdown

  #128 opened a month ago
  0

• Trace Viewer Fails to Show block

  #127 opened a month ago
  0

• logs Analyze fails DB is temporarily unavailable - can't run logs analyze or learn while serving is running

  #126 opened a month ago
  3

• AI Returns text as the language - Cell Won't Be Executable In RunMe

  #125 opened a month ago
  4

• RunMe Service Executor Doesn't Log Response

  #123 opened a month ago
  0

• CodeBlocks nested in lists aren't turned into runnable blocks

  #114 opened a month ago
  3

• Frontend needs to handle Generate returning an error

  #113 opened a month ago
  0

• Ensure errors about invalid OpenAI API keys are properly surfaced

  #112 opened a month ago
  1

• Prompt doesn't properly handle "fill in the middle" of the document use case

  #111 opened 2 months ago
  0

• Update retraining to work with RunMe

  #110 opened a month ago
  7

• Generate a completion failing because of invalid openai api key

  #109 opened a month ago
  8

• bashish improper parsing of valid command

  #104 opened a month ago
  1

• assets download uses CWD

  #103 opened 2 months ago
  5

• vscode-web-assets image isn't built as part of releases

  #99 opened a month ago
  6

• Prettify the trace/eval/logs viewer

  #97 opened 2 months ago
  0

• Example IDs in evaluation should be stable across experiments

  #95 opened 2 months ago
  0

• Use Pebble to store traces

  #91 opened a month ago
  0

• Compute normalized distance

  #90 opened 2 months ago
  0

• Evaluation: Reconciler should ensure experiment parameters haven't changed

  #89 opened 2 months ago
  0

• scrollable element for output doesn't work

  #86 opened a month ago
  1

• Feature : add publish data to huggingface (private datasets repository)

  #85 opened 2 months ago
  2

• Continuously train and relearn

  #84 opened 15 days ago
  7

• Retrying on 429 obscures OpenAI quota limit

  #82 opened 2 months ago
  1

• Viewer should show traces

  #81 opened a month ago
  1

• twitter card images not working on subpages

  #77 opened 2 months ago
  9

• Experiment: Use a threshold on similarity to avoid including irrelevant documents

  #76 opened 2 months ago
  0

• Hugo/Docsy Author not showing up

  #75 opened 2 months ago
  1

• Add blogs to foyle.io

  #73 opened 2 months ago
  1

• Setup Google Analytics For Foyle.IO

  #72 opened 2 months ago
  1

• Viewer should render LLM traces

  #68 opened 2 months ago
  1

• BlockLogViewer should have a table of blocklogs

  #67 opened 2 months ago
  0