Skip to content

Releases: agential-ai/agential

v0.2.1

06 Nov 06:00
Compare
Choose a tag to compare

v0.2.0

06 Nov 04:48
9fadbba
Compare
Choose a tag to compare

What's Changed

  • Simple Baselines (CoT, Vanilla, Retries, Warming), Renaming Agent Classes, Adding Prompting component & core module by @alckasoc in #261
  • Evaluation Metrics, Fix-ups, Output Parsing for Evaluation by @alckasoc in #263
  • CLIN Agent by @alckasoc in #267

Full Changelog: v0.1.0...v0.2.0

v0.1.0

28 Aug 08:57
Compare
Choose a tag to compare

What's Changed

  • Migrating Away from LangChain -> LiteLLM & Logging for Token Usage, Cost, and Latency by @alckasoc in #252
  • Yet Another Rigorous, Robust Refactor (YARRR) by @alckasoc in #256
  • Bump aiohttp from 3.9.5 to 3.10.2 by @dependabot in #260

Full Changelog: v0.0.5...v0.1.0

v0.0.5

05 Aug 00:57
b71ec62
Compare
Choose a tag to compare

What's Changed

  • Standardize Output Dictionaries, Mock API Calls, Math (GSM8K, SVAMP, TabMWP) for Reflexion by @alckasoc in #186
  • Standardizing Critique Prompts for CRITIC Benchmarks by @tedasdf in #187
  • Structured Outputs with Pydantic for CRITIC (QA, Math, Code) by @emmalin-7 in #183
  • Let's get this done by @alckasoc in #196
  • Code for Reflexion (HumanEval, MBPP) by @alckasoc in #191
  • Structured Outputs for ReAct with Pydantic by @emmalin-7 in #197
  • Structured Outputs for Reflexion with Pydantic, Outputs Module by @alckasoc in #198
  • Bump urllib3 from 2.1.0 to 2.2.2 by @dependabot in #199
  • Bump urllib3 from 2.2.1 to 2.2.2 in /docs by @dependabot in #200
  • NO MORE FEWSHOT EXAMPLES PLEASEEEEEEEE by @alckasoc in #202
  • TSOM by @alckasoc in #201
  • Universal Selector by @alckasoc in #203
  • Bump certifi from 2023.11.17 to 2024.7.4 by @dependabot in #204
  • Bump certifi from 2024.2.2 to 2024.7.4 in /docs by @dependabot in #205
  • Self-Refine, Refactoring Self-Refine, Math for Self-Refine (GSM8K, SVAMP, TabMWP) by @alckasoc in #225
  • QA for Self-Refine (HotpotQA, FEVER, AmbigNQ, TriviaQA) by @alckasoc in #227
  • Standardize CRITIC/Self-Refine Few-shots for Math, Standardize error types in Reflexion with CRITIC/SR, Code for Self-Refine (HumanEval, MBPP) by @alckasoc in #228
  • Refactor ExpeL for Strategies & Factory Modules, QA/Math/Code for ExpeL, Structured Output for ExpeL, Notebook for ExpeL, Trim Base Classes by @alckasoc in #231
  • Language Agent Tree Search (LATS), QA (HotpotQA, FEVER, AmbigNQ, TriviaQA) for LATS, Notebook for QA LATS, Strategies Module QA for LATS/Structured Outputs by @alckasoc in #244
  • Math & Code for LATS by @alckasoc in #248
  • Bump torch from 2.1.2 to 2.2.0 by @dependabot in #249
  • Bump setuptools from 69.0.3 to 70.0.0 by @dependabot in #250

New Contributors

Full Changelog: v0.0.4...v0.0.5

v0.0.4

23 Jun 06:12
Compare
Choose a tag to compare

What's Changed

  • GSM8k, SVAMP, TabMWP for ReAct by @alckasoc in #166
  • Refactoring ReflexionCoT/ReflexionReAct (a bit of ExpeL), QA (FEVER, AmbigNQ, TriviaQA) for Reflexion, RIP Self-Refine by @alckasoc in #169

Full Changelog: v0.0.3...v0.0.4

v0.0.3

01 Jun 02:16
Compare
Choose a tag to compare

What's Changed

New Contributors

Full Changelog: v0.0.2...v0.0.3

v0.0.2

28 Apr 03:43
Compare
Choose a tag to compare

What's Changed

New Contributors

Full Changelog: v0.0.1...v0.0.2

v0.0.1

23 Apr 20:04
Compare
Choose a tag to compare

What's Changed

New Contributors

Full Changelog: https://github.com/alckasoc/agential/commits/0.0.1