Version 0.9.0

[mandel]

New Features

The main new features are:

• contribute to a file or standard input and error
• @pdl Python decorator

contribute to files

The user can declare a file aggregator that can be used in the contribute to accumulate the results of the blocks.
For example, in the following program, an aggregator named log associated to the file /tmp/log.txt is declared.
This aggregator is used to store the output of the model in the file /tmp/log.txt.

defs:
  log:
    aggregator: 
      file: /tmp/log.txt
text:
- Hello
- model: ollama_chat/granite3.3:2b
  contribute: [ result, context, log ]

By default, the aggregator stdin and stderr are available to contribute to the standard input and standard error.
It is useful, for example to outpout debug information. In the following program, the raw output of the model is emitted
on the standard error:

text:
- Hello
- model: ollama_chat/granite3.3:2b
  modelResponse: raw_response
  contribute:
    - result
    - context
    - stderr:
        value: ${raw_response}

@pdl Python decorator

In order to make it easy to define functions as PDL programs, we provide a @pdl decorator.

from pdl.pdl import pdl

@pdl
def chain_of_thought(scope):
    """
    lastOf:
    - "Question: ${ question }\n"
    - "Answer: Let's think step by step. "
    - model: ollama_chat/granite3.3:2b
      parameters:
          stop:
          - "<|endoftext|>"
          - "Question:"
          include_stop_sequence: false
    """
    return

def main():
    result = chain_of_thought(
        scope={"model": "ollama_chat/granite3.2:2b", 
               "question": "How to write Hello World in OCaml?\n"}
    )
    print(result)

if __name__ == "__main__":
    main()

In this example, the function chain_pf_thought is a string representing a PDL program. The free variables in the string are values passed in the dictionary scope given on argument.

What's Changed

• tests: update expected result by @mandel in tests: update expected result #1158
• First class aggregators by @mandel in First class aggregators #706
• refactor: react pattern in prompt library by @mandel in refactor: react pattern in prompt library #1162
• PDL Python decorator by @vazirim in PDL Python decorator #1166
• fix: type error location by @mandel in fix: type error location #1169
• refactor: interpreter by @mandel in refactor: interpreter #1170
• fix: return the value not the future when a closure is called fro jin… by @mandel in fix: return the value not the future when a closure is called fro jin… #1208
• feat: the scope of the content field is local by @mandel in feat: the scope of the content field is local #1225
• feat: replay an execution by @mandel in feat: replay an execution #1211
• refactor: performance optimizations by @mandel in refactor: performance optimizations #1228
• feat: add event_loop to the interpreter config by @mandel in feat: add event_loop to the interpreter config #1235
• feat: do not reload library when importing multiple time a file by @mandel in feat: do not reload library when importing multiple time a file #1243
• feat: structuredDecoding field on the model block by @mandel in feat: structuredDecoding field on the model block #1250
• docs: update type checking and structured decoding in the tutorial by @mandel in docs: update type checking and structured decoding in the tutorial #1254
• feat: improve error messages by @mandel in feat: improve error messages #1259
• fix: imported files can use stdlib by @mandel in fix: imported files can use stdlib #1264
• fix: improve error messages by @mandel in fix: improve error messages #1276
• fix: avoid catching KeyboardInterrupt by @mandel in fix: avoid catching KeyboardInterrupt #1298
• fix: bug in ipython code block by @mandel in fix: bug in ipython code block #1314
• refactor: use TypedDict for exec program output by @mandel in refactor: use TypedDict for exec program output #1322
• feat: do not dump location tables in the trace by @mandel in feat: do not dump location tables in the trace #1326
• feat: collect global statistics on LLM usage by @mandel in feat: collect global statistics on LLM usage #1328
• feat: add llm_usage to the exec_* config by @mandel in feat: add llm_usage to the exec_* config #1331

Full Changelog: v0.8.0...v0.9.0

---

This discussion was created from the release Version 0.9.0.