summary: AWS Bedrock instrumentation #2314
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* First pass at Bedrock integration tests * Response payloads do not have a model ID * Fixed issue with errors getting dropped; Fixed Titan Embedded response model * Adding custom attributes test * Test fixes and cleanup * Added AwsBedrockConfiguration * Fix issue with embedding event * Fixing intermittent test failures * Add new integration tests to workflows * Reduce test timeout
chynesNR
changed the title
nrcventura
reviewed
Mar 19, 2024
nrcventura
reviewed
Mar 19, 2024
src/Agent/NewRelic/Agent/Extensions/NewRelic.Agent.Extensions/Api/IAgentApi.cs
Outdated
Show resolved
Hide resolved
nrcventura
reviewed
Mar 19, 2024
src/Agent/NewRelic/Agent/Extensions/NewRelic.Agent.Extensions/Llm/EventHelper.cs
Show resolved
Hide resolved
nrcventura
reviewed
Mar 19, 2024
src/Agent/NewRelic/Agent/Extensions/Providers/Wrapper/Bedrock/Bedrock.csproj
Outdated
Show resolved
Hide resolved
nrcventura
reviewed
Mar 19, 2024
src/Agent/NewRelic/Agent/Extensions/Providers/Wrapper/Bedrock/InvokeModelAsyncWrapper.cs
Outdated
Show resolved
Hide resolved
nr-ahemsath
reviewed
Mar 19, 2024
src/Agent/NewRelic/Agent/Extensions/Providers/Wrapper/Bedrock/InvokeModelAsyncWrapper.cs
Outdated
Show resolved
Hide resolved
nrcventura
reviewed
Mar 20, 2024
src/Agent/NewRelic/Agent/Extensions/Providers/Wrapper/Bedrock/InvokeModelAsyncWrapper.cs
Show resolved
Hide resolved
nrcventura
approved these changes
Mar 26, 2024
* Move Json deserialization from wrapper to core * Also needed to move the models to core as well * Add and tweak comments/readme
chynesNR
changed the title
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #2314 +/- ##
==========================================
- Coverage 80.53% 80.47% -0.06%
==========================================
Files 441 450 +9
Lines 27631 27942 +311
Branches 2989 3023 +34
==========================================
+ Hits 22252 22487 +235
- Misses 4611 4682 +71
- Partials 768 773 +5
Flags with carried forward coverage won't be shown. Click here to find out more.
|
nrcventura
approved these changes
Apr 2, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
feat: Add auto-instrumentation for AWS Bedrock
feat: New configuration options are available specific to AI monitoring.
feat: A new AI monitoring related public API method has been added - SetLlmTokenCountingCallback
notice: New Relic AI monitoring is the industry’s first APM solution that provides end-to-end visibility for AI Large Language Model (LLM) applications. It enables end-to-end visibility into the key components of an AI LLM application. With AI monitoring, users can monitor, alert, and debug AI-powered applications for reliability, latency, performance, security and cost. AI monitoring also enables AI/LLM specific insights (metrics, events, logs and traces) which can easily integrate to build advanced guardrails for enterprise security, privacy and compliance.
notice: AI monitoring offers custom-built insights and tracing for the complete lifecycle of an LLM’s prompts and responses, from raw user input to repaired/polished responses. AI monitoring provides built-in integrations with popular LLMs and components of the AI development stack. This release provides instrumentation for AWS Bedrock.
notice: When AI monitoring is enabled, the agent will now capture AI LLM related data. This data will be visible under a new APM tab called AI Responses. See our AI Monitoring documentation for more details.