Version 0.6.1

What's Changed

• feat: update rust python support to pull in python stdlib by @starpit in #877
• feat: port rust model pull logic to use rust AST by @starpit in #875
• fix: avoid openssl in rust app for now by @starpit in #880
• gsm8k multi-plan, tree-of-thought, tree-of-thought with few shots by @vazirim in #881
• feat: rust interpreter support for modelResponse, ollama-rs tooling calling, and no-stream by @starpit in #883
• chore: minor code cleanups to rust interpreter by @starpit in #884
• test: update github action rust interpreter test to remove ollama pull by @starpit in #885
• fix: add kind tags to rust ast blocks by @starpit in #887
• fix: update rust interpreter to avoid global emit/scope state by @starpit in #888
• fix: rust pull logic may not always pull by @starpit in #889
• feat: remove tauri cli support for running python interpreter by @starpit in #890
• chore: bump rust dependencies to resolve alert by @starpit in #893
• test: tauri github actions test should apt install the deb by @starpit in #892
• feat: support for --data and --data-file in rust interpreter by @starpit in #894
• fix: begin phasing in Metadata (common defs, etc. attrs) into rust AST by @starpit in #895
• chore: update granite-io dependency by @mandel in #896
• refactor: move def attr into Metadata (rust interpreter) by @starpit in #897
• feat: introduce Expr typing and apply it to IfBlock.condition by @starpit in #899
• feat: update rust Call AST to use Expr for condition attr by @starpit in #901
• chore: bump to rust 2024 edition by @starpit in #902
• feat: continue to flesh out block metadata structure in rust by @starpit in #898
• refactor: add metadata attr to remaining rust block asts by @starpit in #903
• feat: update rust Repeat AST to use Expr for for attr by @mandel in #904
• refactor: introduce Advanced enum to rust AST by @starpit in #906
• refactor: refactor rust ast to place metadata in common struct by @starpit in #909
• fix: improve deserialization of python-generated model block traces by @starpit in #910
• fix: in rust ast, allow ModelBlock model to be an expr by @starpit in #911
• feat: initial pdl__id and --trace support for rust interpreter by @starpit in #912
• fix: update rust interpreter to create Data blocks for expr eval, and model_input trace field by @starpit in #914
• fix: populate trace context field in rust interpreter by @starpit in #915
• Update stop sequences in parameters by @jgchn in #861
• refactor: extract platform-generic logic from run_ollama_model() handler by @starpit in #916
• fix: rust interpreter was not handling pdl__context for re-runs of traces by @starpit in #917
• feat: improve support for importing stdlib in python code blocks by @starpit in #918
• skeleton-of-thought example by @vazirim in #919
• Bump litellm and openai versions by @vazirim in #920
• fix: improve support for rust interpreter python imports from venv by @starpit in #922
• chore: bump tauri and npm dependencies by @starpit in #923
• chore: bump ui to 0.6.1 by @starpit in #921

Full Changelog: v0.6.0...v0.6.1

Version 0.6.0

This new release has two major changes:

• pdl-lint, a linter for PDL programs (thanks to @vite-falcon!)
• mesages in the context with the same role are not automatically merged anymore.

For example, the following program generates 3 messages:

lastOf:
  - role: user
    text:
      - hello
      - "\n"
      - world
  - ${pdl_context}

result:

[{"role": "user", "content": "hello", "defsite": "lastOf.text.0"}, {"role": "user", "content": "\n", "defsite": "lastOf.text.1"}, {"role": "user", "content": "world", "defsite": "lastOf.text.2"}]

To generate only one message, you have to use a message block:

lastOf:
  - role: user
    content:
      text:
        - hello
        - "\n"
        - world
  - ${pdl_context}

result

[{"role": "user", "content": "hello\nworld", "defsite": "lastOf.message"}]

What's Changed

• Switch to granite-io version 0.2 by @mandel in #818
• feat: update beeai compiler to support compiling directly from python source by @starpit in #834
• Examples restructuring, tutorial changes by @vazirim in #836
• Bug fixes for setting default parameters by @vazirim in #838
• fix: pdl view trace.json fixes by @starpit in #843
• fix: Bug in pdl_schema_error_analyzer that raises exception during analysis by @vite-falcon in #851
• Clean up run examples and automate result updating via GH Actions by @jgchn in #853
• feat: do not merge messages with same role by @mandel in #846
• fixes to react examples by @vazirim in #859
• feat: message blocks contribute the message instead of the content to the context by @mandel in #862
• feat: do not stringify messages content by @mandel in #858
• feat: rust interpreter by @starpit in #857
• gsm8k plan with few-shots by @vazirim in #870
• feat: add pdl-lint tool that can be configured via pyproject.toml by @vite-falcon in #864

New Contributors

• @vite-falcon made their first contribution in #851

Full Changelog: v0.5.1...v0.6.0

Version 0.5.1

What's Changed

• Fix parsing of localized expressions by @mandel in #804
• fix: update ui to support pulling interpreter from local dir by @starpit in #807
• fix: interpreter squashes PdlRuntimeErrors by @starpit in #800
• fix: interpreter fails when passed parameters with null/None values by @starpit in #809
• Rename expr field of LocalizedExpression into pdl__expr by @mandel in #806
• feat: compile bee to pdl by @starpit in #817
• fix: rerun in ui bombs by @starpit in #819
• fix: async model call prints should only occur if PDL_VERBOSE_ASYNC env is set by @starpit in #820
• fix: skip litellm 1.63.14 by @starpit in #827
• fix: pin openai==1.61.0 pip due to breaking change on their side by @starpit in #829

Full Changelog: v0.5.0...v0.5.1

Version 0.5.0

What's Changed

• feat: add model token usage stats to trace by @starpit in #762
• feat: add support for CodeBlocks with argv by @starpit in #756
• feat: add Usage tab to detail drawer for model blocks by @starpit in #778
• Systematically used localized expressions in the trace and add pdl__result in them by @mandel in #760
• feat: add Result tab to detail drawer by @starpit in #782
• doc: update readme ui screenshot to show usage metrics by @starpit in #793
• Copy the schema on the website by @mandel in #797

Full Changelog: v0.4.2...v0.5.0

Version 0.4.2

What's Changed

• feat: in UI allow pty execution to be canceled by @starpit in #673
• feat: switch ui tile run menu to split action dropdown by @starpit in #675
• default parameters for ollama_chat models by @vazirim in #689
• Change examples to ollama_chat by @jgchn in #691
• Grade School Math example by @esnible in #694
• Docstrings and examples for PDL concepts by @esnible in #693
• feat: ui temperature stability by @starpit in #697
• feat: add Pagination to UI by @starpit in #704
• demo hallucination trace by @vazirim in #705
• Structured decoding bug fix for watsonx, ollama + traceback for python code blocks by @vazirim in #708
• feat: interpreter should report (stderr) call start/end and timing by @starpit in #711
• feat: update interpreter to print out model response messages in async mode by @starpit in #717
• Update parse_str interface by @mandel in #741
• Support dev version of granite-io by @mandel in #742
• feat: pull models in rust by @starpit in #743
• feat: update auto-pull logic to run in parallel with pip install by @starpit in #744
• feat: use shasum as cache key for venv by @starpit in #748
• feat: add gsm8k demo to ui (demo9) by @starpit in #753
• Contributed values are expressions by @mandel in #754
• Use ${ pdl_context } as default value for the input field of a model block by @mandel in #757
• added litellm param to ignore structure decoding param in tools example by @vazirim in #750
• gsm8k with planning by @vazirim in #761

Full Changelog: v0.4.1...v0.4.2

Version 0.4.1

What's Changed

• Update granite-io dependency by @mandel in #641

Full Changelog: v0.4.0...v0.4.1

Version 0.4.0

What's Changed

• gsm8k examples and results by @vazirim in #322
• feat: in react ui Context tab, use breadcrumb ui to link to def site by @starpit in #380
• Add json-repair by @claudiosv in #279
• feat: in react ui, add Masonry view to replace Transcript view by @starpit in #395
• Asynchronous LLMs calls by @mandel in #284
• feat: in react UI, add Run button to support re-running program by @starpit in #431
• Add a max_iterations field to the repeat/until loop (and make until optional) and remove repeat/num_iterations loops. by @mandel in #434
• Granite 3.1 chat template fix by @vazirim in #433
• feat: add homebrew formula by @starpit in #447
• Unify repeat and for loops and add while by @mandel in #444
• feat: in react ui re-enable Replay/Run button and functionality by @starpit in #451
• intrinsics hallucination example by @vazirim in #464
• doc: update react ui build for production documentation by @starpit in #476
• feat: syntax highlight code in markdown blocks by @starpit in #480
• feat: in react ui, use pty for Run by @starpit in #492
• feat: add final result 'output of program' to react ui masonry by @starpit in #497
• removed old viewer by @vazirim in #510
• feat: add Platform field to model detail Summary tab by @starpit in #516
• modules implementation by @vazirim in #507
• New RAG example by @esnible in #427
• feat: initial support for showing structured model responses in detail ui by @starpit in #527
• updated PDL quick reference by @hirzel in #545
• feat: add opengraph meta info to ui by @starpit in #549
• Migrate some examples from Replicate to Ollama by @jgchn in #522
• Added Granite 3.2 chat template, template that works with ollama by @vazirim in #557
• model blocks can use the granite-io platform by @mandel in #529
• Join loop iterations as objects by @mandel in #580
• Add flexibility on the case of the values for the fields lang, parser, and mode by @mandel in #612
• Incorrect endpoint in Telemetry doc by @esnible in #619
• Deploy Ollama to run examples by @jgchn in #629

New Contributors

• @jgchn made their first contribution in #521

Full Changelog: v0.3.0...v0.4.0

Version 0.3.0

What's Changed

• Port pdl-live to react+patternfly+vite by @starpit in #253
• Embed PDL interpreter into react (tauri) app builds by @starpit in #350
• Remove BAM support by @mandel in #265
• Config options for model default parameters by @esnible in #266
• Add a match block by @mandel in #252
• Don't crash without log on keyboard exit by @esnible in #346
• lowered lower bound of litellm to 1.57.3 by @vazirim in #365

New Contributors

• @starpit made their first contribution in #253

Full Changelog: v0.2.0...v0.3.0

Version 0.2.0

Warning: This release introduce a non-backward compatible change: call blocks take closures as argument instead of function names. In practice, a function call like call: f must be replace by call: ${f}.

What's Changed

• The argument of call: is a closure, not a name by @mandel in #242
• Initial OpenTelemetry support by @esnible in #254
• Removed upper bound on LiteLLM version by @vazirim in #255
• Add comments to examples to make them more obvious by @esnible in #259

Full Changelog: v0.1.1...v0.2.0

Version 0.1.1

What's Changed

• remove None valued parameters when calling LLMs by @vazirim in #212
• Flush the output after each print in streaming mode by @mandel in #213
• support for expressions in function call args by @vazirim in #221
• Show the model name, and request info if possible, on error by @esnible in #226

New Contributors

• @trsudarshan made their first contribution in #209
• @esnible made their first contribution in #222

Full Changelog: v0.1.0...v0.1.1