epam/ai-dial-adapter-bedrock

The project implements AI DIAL API for language models from AWS Bedrock

What's novel

The project implements AI DIAL API for language models from AWS Bedrock

Code Analysis

17 files read · 5 rounds

A DIAL API adapter that unifies AWS Bedrock LLM APIs (Claude, Llama, Stability AI, Cohere, etc.) into a consistent interface for chat completions, embeddings, tokenization, and prompt truncation.

Strengths

Comprehensive model support with clean abstraction layers, sophisticated prompt truncation algorithm with partition-based token counting, and flexible authentication (API keys, AWS credentials, assume role).

Weaknesses

Heavy reliance on external SDKs (aidial-adapter-anthropic, aidial-sdk) limits standalone utility, and large match statements in factory/adapter routing could be more config-driven.

Score Breakdown

Innovation

4 (25%)

Craft

86 (35%)

Traction

39 (15%)

Scope

87 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+1

Craft

Ci+5

Tests+8

Polish+3

Releases+4

Has License+5

Code Quality+24

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+5

Has Dependency Mgmt+5

Traction

Forks+12

Stars+12

Hn Points+0

Watchers+10

Early Traction+0

Devto Reactions+0

Community Contribs+5

Scope

Commits+8

Languages+8

Subsystems+10

Bloat Penalty+0

Completeness+7

Contributors+8

Authored Files+15

Readme Code Match+3

Architecture Depth+7

Implementation Depth+8

Evidence

Commits

139

Contributors

Files

130

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

Apache-2.0