HandyLLM v0.8.2

Release HandyLLM v0.8.2.

Added

• hprompt: load methods now support cls parameter for prompt type specification
• ChatPrompt and CompletionsPrompt support optional request and meta
• ChatPrompt :
  • supports add dict
  • add add_message(...) method
• CompletionsPrompt:
  • add add_text(...) method
• PromptConverter: yaml.dump uses allow_unicode=True option
• move all type definitions to _types.py
• support for package development:
  • add requirement.txt for development
  • add scripts/test.sh for running tests
  • add test scripts in tests folder

Fixed

• HandyPrompt.eval(...) should not make directories for output paths
• CompletionsPrompt._run_with_client(...): misplaced run_config param
• PromptConverter
  • fix variable replacement for content_array message
  • fix wrong return type of stream_msgs2raw and astream_msgs2raw
• requestor:
  • httpx.Response should use reason_phrase to get error reason
  • acall() fix missing brackets for await
  • _call_raw() and _acall_raw() intercept and raise new exception without original one
  • _acall_raw(): read the response first to prevent httpx.ResponseNotRead before getting error message
• _utils.exception2err_msg(...) should append error message instead of printing
• change io.IOBase to IO[str] for file descriptors (e.g. RunConfig.output_fd)
• fix other type hints

Changed

• move all old files in tests folder to examples folder

HandyLLM v0.8.1

Release HandyLLM v0.8.1.

Fixed

• fix the debug print issue when outputting to a file in stream mode

HandyLLM v0.8.0

Release HandyLLM v0.8.0.

Added

• CLI: output to stderr without buffering
• add RunConfig.output_path_buffering for controlling buffering of output file
• add this changelog

Fixed

• fix _post_check_output(...) not using evaluated run_config (may cause output_path or output_fd to be ignored)

Changed

• rename internal constants to remove leading _ of API_xxx constants

Removed

• remove unused files in deprecated folder

HandyLLM v0.7.6

Release HandyLLM v0.7.6.

Added

• add RunConfig.on_chunk as callback for streamed chunks
• add Azure tts example
• add VM method to transform kwargs to % wrapped variable map dict
• add var_map arg to eval(...), run(...) and arun(...) for convenience

Changed

• merging different versions of var_map from method argument or from another RunConfig, instead of replacing it as a whole
• rename RunConfig.to_dict's retain_fd arg to retain_object

HandyLLM v0.7.5

Release HandyLLM v0.7.5.

Added

• OpenAIClient add audio speech (tts) api support
  • add azure support for audio speech and transcriptions
• add tts test script

Changed

• prioritize RunConfig.output_evaled_prompt_fd over RunConfig.output_evaled_prompt_path
• eval(...)
  • always return a new object
  • gives run_config arg a default value
  • accepts kwargs, same as run(...)
• when dumping, always filter request
• credential file do not overwrite existing request args

Fixed

• non-stream mode prioritize RunConfig.output_fd over RunConfig.output_path

HandyLLM v0.7.4

Release HandyLLM v0.7.4.

HandyLLM v0.7.3

Release HandyLLM v0.7.3.

HandyLLM v0.7.2

Release HandyLLM v0.7.2.

HandyLLM v0.7.1

Release HandyLLM v0.7.1.

HandyLLM v0.7.0

Release HandyLLM v0.7.0.