Releases: EinStack/glide
v0.1.0-rc.1
The first major update with breaking changes to the language chat schemas
and begging of work on instrumenting the gateway with OpenTelemetry.
Added
- 🔧 Use github.com/EinStack/glide as module name to support go install cmd (@gernest)
- ✨🔧 Setup Open Telemetry Metrics and Traces (#237) (@gernest)
- 🔧 #221 Add B3 trace propagator (#242) (@gernest)
- 🔧 #241 Support overriding OTEL resource attributes (#243) (@gernest)
- 🔧 #248 Disable span and metrics by default (#254) (@gernest)
- 🔧 #220 Instrument API server with observability signals (#255) (@gernest)
- 🔧 #164 Make client connection pool configurable across all providers (#251) (@daesu)
- 🔧 Instrument gateway process (#256) (@gernest)
- 🔧 #262: adding connection pool for chat request and response (#271) (@tom-fitz)
Changed
- 🔧 #238 Implements human-readable durations in config (#253) (@ppmdo)
- 🔧 #266: removing omitempty from response definition (#267) (@tom-fitz)
Breaking Changes
- 🔧 💥 #235: Extended the non-streaming chat error schema with new fields to give clients more context around the error (#236) (@roma-glushko)
- 💥 Convert all camelCase config fields to the snake_case in the provider configs (#260) (@roma-glushko)
- ✨💥 #153: Allow to pass multiple model-specific param overrides (#264) (@roma-glushko)
Fixed
- 🐛 #217: Set build info correctly in Glide images (#218) (@roma-glushko)
Security
- 🔒 Updated golang to 1.22.4 to address CVE-2024-24790 (#276) (@STAR-173)
Miscellaneous
- 📝 Defined a way to manage EinStack Glide project (#234) (@roma-glushko)
- 👷 #219: Setup local telemetry stack with Jaeger, Grafana, VictoriaMetrics and OTEL Collector (#225) (@roma-glushko)
- 👷♂️ Added a new GH action to watch for glide activity stream (#239, #244) (@roma-glushko)
- ✨ Switched to the new docs (@roma-glushko)
- 🔧 #240: Automatically install air (#277, #270) (@ppmdo, @roma-glushko)
Full Changelog: 0.0.3...0.1.0-rc.1
📦 v0.0.3: Streaming Chat
Summary
✨ Bringing support for streaming chat in Glide (integrated with OpenAI, Azure OpenAI and Cohere)
✨ Started handling 401 errors to mark models as premaritally unavailable (e.g. when API key was not correct)
🐛 Fixing the panic related to swagger.yaml file
🐛 Fixing Anthropic chat workflow by passing API key correctly
🔧 Improved Cohere param config and validation
Changelog
Added
- ✨Streaming Chat Workflow #149 #163 #161 (@roma-glushko)
- ✨Streaming Support for Azure OpenAI #173 (@mkrueger12)
- ✨Cohere Streaming Chat Support #171 (@mkrueger12)
- ✨Start counting token usage in Anthropic Chat #183 (@roma-glushko)
- ✨Handle unauthorized error in health tracker #170 (@roma-glushko)
- 🔧 #195 #196: Set router ctx in stream chunks & handle end of stream in case of some errors (@roma-glushko)
- 🐛🔧 #197: Handle max_tokens & content_filtered finish reasons across OpenAI, Azure and Cohere (@roma-glushko)
Changed
- 🔧 💥 #198: Expose more Cohere params & fixing validation of provider params in config (breaking change) (@roma-glushko)
- 🔧 #186: Rendering Durations in a human-friendly way (@roma-glushko)
Fixed
- 🐛 Fix Anthropic API key header #183 (@roma-glushko)
- 🐛 #209: Embed Swagger specs into binary to fix panics caused by missing swagger.yaml file (@roma-glushko)
- 🐛 #200: Implemented a custom json per line stream reader to read Cohere chat streams correctly (@roma-glushko)
Security
- 🔓 Update crypto lib, golang, fiber #148 (@roma-glushko)
Miscellaneous
- 🐛 Update README.md to fix helm chart location #167 (@arjunnair22)
- 🔧 Updated .go-version (@roma-glushko)
- ✅ Covered the telemetry by tests #146 (@roma-glushko)
- 📝 Separate and list all supported capabilities per provider #190 (@roma-glushko)
v0.0.3-rc.2
Final major improvements to streaming chat workflow. Fixed issues with Cohere streaming chat.
Expanded and revisited Cohere params in config.
Added
- 🔧 #195 #196: Set router ctx in stream chunks & handle end of stream in case of some errors (@roma-glushko)
- 🐛🔧 #197: Handle max_tokens & content_filtered finish reasons across OpenAI, Azure and Cohere (@roma-glushko)
Changed
- 🔧 💥 #198: Expose more Cohere params & fixing validation of provider params in config (breaking change) (@roma-glushko)
- 🔧 #186: Rendering Durations in a human-friendly way (@roma-glushko)
Fixed
- 🐛 #209: Embed Swagger specs into binary to fix panics caused by missing swagger.yaml file (@roma-glushko)
- 🐛 #200: Implemented a custom json per line stream reader to read Cohere chat streams correctly (@roma-glushko)
📦 v0.0.3-rc.1
A new release candidate that includes the new streaming chat functionality.
Added
- ✨Streaming Chat Workflow #149 #163 #161 (@roma-glushko)
- ✨Streaming Support for Azure OpenAI #173 (@mkrueger12)
- ✨Cohere Streaming Chat Support #171 (@mkrueger12)
- ✨Start counting token usage in Anthropic Chat #183 (@roma-glushko)
- ✨Handle unauthorized error in health tracker #170 (@roma-glushko)
Fixed
- 🐛 Fix Anthropic API key header #183 (@roma-glushko)
Security
- 🔓 Update crypto lib, golang, fiber #148 (@roma-glushko)
Miscellaneous
- 🐛 Update README.md to fix helm chart location #167 (@arjunnair22)
- 🔧 Updated .go-version (@roma-glushko)
- ✅ Covered the telemetry by tests #146 (@roma-glushko)
- 📝 Separate and list all supported capabilities per provider #190 (@roma-glushko)
📦 v0.0.2
A new incremental release of Glide 🐦
Changelog
Features
- ✨#117 Allow to load dotenv files (@roma-glushko)
- ✨ #142: [Lang Chat Router] Ollama Support (@mkrueger12)
- ✨ #131: [Lang Chat Router] AWS Bedrock Support (@mkrueger12)
Improvements
- ✨👷#91 Support for Windows (@roma-glushko)
- 👷 #139 Build Glide for OpenBSD and ppc65le, s390x, riscv64 architectures (@roma-glushko)
Miscellaneous
- 👷 #92 Release binaries to Snapcraft (@roma-glushko)
- 👷 #123 publish images to DockerHub (@roma-glushko)
- 🔧 #136 Migrated all API to Fiber (@roma-glushko)
- 👷 #139 Create a image tag with pure version (without distro suffix) (@roma-glushko)
- 👷 #155 Fixing the dockerhub authorization step in the release workflow (@roma-glushko)
- ♻️ #151: Moved specific provider schemas closer to provider's packages (@roma-glushko)
v0.0.2-rc.2
Changelog
Features
- ✨ #142: [Lang Chat Router] Ollama Support (@mkrueger12)
- ✨ #131: [Lang Chat Router] AWS Bedrock Support (@mkrueger12)
Miscellaneous
- 👷 #155 Fixing the dockerhub authorization step in the release workflow (@roma-glushko)
- ♻️ #151: Moved specific provider schemas closer to provider's packages (@roma-glushko)
v0.0.2-rc.1
A new release candidate for upcoming Glide v0.0.2 with several compatibility improvements (the most notable is a native Windows support) and ability to load secrets from dotenv files.
Changelong
Features
- ✨#117 Allow to load dotenv files (@roma-glushko)
Improvements
- ✨👷#91 Support for Windows (@roma-glushko)
- 👷 #139 Build Glide for OpenBSD and ppc65le, s390x, riscv64 architectures (@roma-glushko)
Miscellaneous
- 👷 #92 Release binaries to Snapcraft (@roma-glushko)
- 👷 #123 publish images to DockerHub (@roma-glushko)
- 🔧 #136 Migrated all API to Fiber (@roma-glushko)
- 👷 #139 Create a image tag with pure version (without distro suffix) (@roma-glushko)
v0.0.1 (Private Preview) 🎉
This is the first "stable" release of Glide gateway as we have finished our Private Preview milestone 🎉🎉🎉
As a part of this initial scope, we had to setup a bunch of common things to make it roll. As for the core functionality, we have brought up:
- The routing functionality with four types of routing strategies (including a tricky one like the least latency routing)
- The first-class adaptive resiliency & fallbacking across all routing strategies
- Unified Chat API that supports popular model providers like OpenAI, Azure OpenAI (on-prem models), Cohere, OctoML, Anthropic
- The ability to have model-specific prompts
- Installation via Docker & Homebrew
The most exciting things are ahead of us, so looking forward to get more cool stuff in scope of Public Preview 🚀 🚀 🚀
Let's equip GenAI revolution with a resilient open infrastructure 🙌
📦 Release: https://github.com/EinStack/glide/releases/tag/0.0.1
📚 Docs: https://glide.einstack.ai/
📺 Demo: https://github.com/EinStack/glide-demo
🗺️ Roadmap: https://github.com/EinStack/glide/blob/develop/ROADMAP.md
Changelog
Features
- ✨ #81: Allow to chat message based for specific models (@mkrueger12)
Improvements
- 🔧 #78: Normalize response latency by response token count (@roma-glushko)
- 📝 #112 added the CLI banner info (@roma-glushko)
Miscellaneous
- 📝 #114 Make links actual across the project (@roma-glushko)
v0.0.1-rc.2
Changelog
Improvements
- ⚙️ [config] Added validation for config file content #40 (@roma-glushko)
- ⚙️ [config] Allowed to pass HTTP server configs from config file #41 (@roma-glushko)
- 👷 [build] Allowed building Homebrew taps for release candidates #99 (@roma-glushko)
v0.0.1-rc.1
The first ever release candidate 🚀🚀🚀
Features
- ✨ [providers] Support for OpenAI Chat API #3 (@mkrueger12 )
- ✨ [API] #54 Unified Chat API (@mkrueger12 )
- ✨ [providers] Support for Cohere Chat API #5 (@mkrueger12 )
- ✨ [providers] Support for Azure OpenAI Chat API #4 (@mkrueger12 )
- ✨ [providers] Support for OctoML Chat API #58 (@mkrueger12 )
- ✨ [routing] The Routing Mechanism, Adaptive Health Tracking, and Fallbacks #42 #43 #51 (@roma-glushko)
- ✨ [routing] Support for round robin routing strategy #44 (@roma-glushko)
- ✨ [routing] Support for the least latency routing strategy #46 (@roma-glushko)
- ✨ [routing] Support for weighted round robin routing strategy #45 (@roma-glushko)
- ✨ [providers] Support for Anthropic Chat API #60 (@mkrueger12 )
- ✨ [docs] OpenAPI specifications #22 (@roma-glushko )
Miscellaneous
- 🔧 [chores] Inited the project #6 (@roma-glushko)
- 🔊 [telemetry] Inited logging #14 (@roma-glushko)
- 🔧 [chores] Inited Glide's CLI #12 (@roma-glushko)
- 👷 [chores] Setup CI workflows #8 (@roma-glushko)
- ⚙️ [config] Inited configs #11 (@roma-glushko)
- 🔧 [chores] Automatic coverage reports #39 (@roma-glushko)
- 👷 [build] Setup release workflows #9 (@roma-glushko)