lievan

enable Test_DependencyEnable test for go

5

## Description `Test_DependencyEnable` is passing for go, but not enabled. This PR enables it. ## Motivation ## Additional notes

fix(llmobs): deprecate and convert numerical metrics to score type

3

LLM Obs backend currently does not support ingesting the numerical metric type, so the SDK needs to be updated to 1. warn users not to submit this metric type and...

[ML-OB] document metadata for custom evals

4

### What does this PR do? What is the motivation? This PR documents how to set the `metadata` field for evaluation metrics in the SDK ### Merge instructions - [...

[ML-OB] Prompt template annotations

3

### What does this PR do? What is the motivation? This PR adds instructions on how to annotate a prompt on an LLM span ! Not to be merged yet...

chore(llmobs): implement non skeleton code for ragas faithfulness

3

This PR adds in the non-boiler plate code for the ragas faithfulness evaluator. The majority of LOC changes are from cassettes/requirements. The main logic is in `ddtrace/llmobs/_evaluators/ragas/faithfulness.py`. There are four...

feat(llmobs): track prompt caching for bedrock converse api

3

Tracks number of tokens read from and written to the prompt cache for bedrock converse api https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html Bedrock returns `cacheWrite/ReadInputTokenCount` or `cacheWrite/ReadInputTokens` (not exactly sure why there are two names,...

feat(llmobs): track prompt caching for anthropic sdk

3

Tracks number of tokens read from and written to the prompt cache for anthropic https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching anthropic returns `cache_creation/read_input_tokens` in their usage field. We map these to `cache_write/read_input_tokens` keys in our...

feat(llmobs): track prompt caching for openai chat completions

3

Tracks number of tokens read from the prompt cache for openai chat completions openai does prompt caching by default and returns a `cached_tokens` field in `prompt_tokens_details` https://platform.openai.com/docs/api-reference/chat/create We rely on...