AIGenPipeline Release 2.1.1

This is the next public release of the AIGenPipeline, a tool supporting the use of AI to systematically create text files - code, documentation, you name it. It allows using the OpenAI chat completion API either via a script or via a Java programm, depending on the complexity of your tasks. For each task you provide a prompt file, input files and specify an output file, and the tool checks whether the outputfile has to be generated for the first time or needs to be regenerated because the prompt / input files have changed. For more documentation please consult the project website.

Changes

• Release 2.1.0 adds an option -wvf that allows keeping the version in an external file for brain dead file formats that don't allow comments - e.g. for foo.json we generate / read foo.json.version for checking whether the file needs to be regenerated.
• If you generate many files (e.g., hundreds) the startup time might become an issue. So I've added the option to use command files: if you give just one file argument then from this file it reads an arbitrary number of command lines separated by a blank line - see the homepage for more details.
• Release 2.1.1 adds support for the o1-* models of OpenAI: they do not allow a system message, so that's moved into a first user message (if either the model is named like o1-9? or option -ns / --nosysmsg is given) and instead of the deprecated max_tokens we use max_completion_tokens.

Download

You can either

• build it from the source locally,
• grab the zip from the command line package (on maven central / maven search )
• use the framework jar (on maven central)
  directly with the class AIGenerationTask .

What's Changed

• A couple of dependency bumps by @dependabot
• Introduce Command files by @stoerr in #52
• Add version files for version markers by @stoerr in #53

Full Changelog: aigenpipeline-2.0.1...aigenpipeline-2.1.1

AIGenPipeline Release 2.0.1

This is the next public release of the AIGenPipeline, a tool supporting the use of AI to systematically create text files - code, documentation, you name it. It allows using the OpenAI chat completion API either via a script or via a Java programm, depending on the complexity of your tasks. For each task you provide a prompt file, input files and specify an output file, and the tool checks whether the outputfile has to be generated for the first time or needs to be regenerated because the prompt / input files have changed. For more documentation please consult the project website.

There have been quite a lot of additions:

• Implement an --helpai feature: you can ask a question about the tool
• A new argument -upd / --update to update files in place while minimizing changes
• print a mermaid dependency graph for output scan with -dd
• Add a --hint option to give the AI hints what needs to be changed now
• an elaborate example using it for code duplicate search
• switch the default model from gpt-3.5-turbo to gpt-4o-mini since that's better and also less expensive

Download

You can either

• build it from the source locally,
• grab the zip from the command line package (on maven central / maven search )
• use the framework jar (on maven central)
  directly with the class AIGenerationTask .

What's Changed

• A couple of dependency bumps by @dependabot
• Implement an --helpai feature: you can ask a question about the tool by @stoerr in #24
• Feature/promptinplace by @stoerr in #25
• Implement copy and openaijson pseudo models by @stoerr in #26
• Print a Mermaid dependency graph for -os (output scan) with -dd by @stoerr in #27
• Various fixes and documentation updates by @stoerr in #28
• Add -upd / --update option and --hint option by @stoerr in #30
• docs: update README.md by @eltociear in #29
• Example: code duplicate search by @stoerr in #36
• switch the default model from gpt-3.5-turbo to gpt-4o-mini since that's better and also less expensive

New Contributors

• @eltociear made their first contribution in #29

Full Changelog: aigenpipeline-1.0.0...aigenpipeline-2.0.1

AIGenPipeline Release 1.1.0

This is the next public release of the AIGenPipeline, a tool supporting the use of AI to systematically create text files - code, documentation, you name it. It allows using the OpenAI chat completion API either via a script or via a Java programm, depending on the complexity of your tasks. For each task you provide a prompt file, input files and specify an output file, and the tool checks whether the outputfile has to be generated for the first time or needs to be regenerated because the prompt / input files have changed. For more documentation please consult the project website.

This release adds configuration files, so that it's easier to use various LLM services like Anthropic Claude or local LLMs.
For more details see the pull request or the documentation.

Download

You can either build it locally, grab the zip from the command line package
or use the framework jar directly with the class AIGenerationTask .
Or download it from maven central .

What's Changed

• Add configuration files by @stoerr in #16
• instruct to minimize changes if output file is given as input file by @stoerr in #17

Full Changelog: aigenpipeline-1.0.0...aigenpipeline-1.1.0

AIGenPipeline Release 1.0.0

This is the next public release of the AIGenPipeline, a tool supporting the use of AI to systematically create text files - code, documentation, you name it. It allows using the OpenAI chat completion API either via a script or via a Java programm, depending on the complexity of your tasks. For each task you provide a prompt file, input files and specify an output file, and the tool checks whether the outputfile has to be generated for the first time or needs to be regenerated because the prompt / input files have changed. For more documentation please consult the project website.

This release adds functionality so that the tool can replace just a part of the output file which is delineated by two lines containing a marker given on the command line. That allows easily mixing manually created content with automatically created content in one file. For more details see the pull request or the documentation.

Download

You can either build it locally, grab the zip from the command line package
or use the framework jar directly with the class AIGenerationTask .
Or download it from maven central .

What's Changed

• Replacement of parts in files by @stoerr in #15

New Contributors

• @stoerr made their first contribution in #15

Full Changelog: aigenpipeline-0.2.0...aigenpipeline-1.0.0

AIGenPipeline Release 0.2.0

This is the next public release of the AIGenPipeline, a tool supporting the use of AI to systematically create text files - code, documentation, you name it. It allows using the OpenAI chat completion API either via a script or via a Java programm, depending on the complexity of your tasks. For each task you provide a prompt file, input files and specify an output file, and the tool checks whether the outputfile has to be generated for the first time or needs to be regenerated because the prompt / input files have changed. For more documentation please consult the project website.

The largest change is that it is now available from maven central.

Download

You can either build it locally, grab the zip from the command line package
or use the framework jar directly with the class AIGenerationTask .
Or download it from maven central .

What's Changed

• Now available from maven central
• Bump org.apache.maven.plugins:maven-compiler-plugin from 3.12.1 to 3.13.0 by @dependabot in #14
• Bump org.apache.maven.plugins:maven-source-plugin from 3.1.0 to 3.3.0 by @dependabot in #13
• Bump org.apache.maven.plugins:maven-gpg-plugin from 3.0.1 to 3.2.2 by @dependabot in #12
• Bump org.apache.maven.plugins:maven-assembly-plugin from 3.6.0 to 3.7.1 by @dependabot in #11

Full Changelog: aigenpipeline-0.1.0...aigenpipeline-0.2.0

AIGenPipeline Release 0.1.0

This is the first public release of the AIGenPipeline, a tool supporting the use of AI to systematically create text files - code, documentation, you name it. It allows using the OpenAI chat completion API either via a script or via a Java programm, depending on the complexity of your tasks. For each task you provide a prompt file, input files and specify an output file, and the tool checks whether the outputfile has to be generated for the first time or needs to be regenerated because the prompt / input files have changed. For more documentation please consult the project website.

Download

You can either build it locally, grab the zip from the
command line package
or use the framework jar directly with the class
AIGenerationTask .

Full Changelog: https://github.com/stoerr/AIGenPipeline/commits/aigenpipeline-0.1.0