first commit

.gitignore

@@ -0,0 +1,443 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,java,c++,pycharm,visualstudiocode,macos,linux,windows
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,java,c++,pycharm,visualstudiocode,macos,linux,windows
+
+### C++ ###
+# Prerequisites
+*.d
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+*.dll
+
+# Fortran module files
+*.mod
+*.smod
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+*.lib
+
+# Executables
+*.exe
+*.out
+*.app
+
+### Java ###
+# Compiled class file
+*.class
+
+# Log file
+*.log
+
+# BlueJ files
+*.ctxt
+
+# Mobile Tools for Java (J2ME)
+.mtj.tmp/
+
+# Package Files #
+*.jar
+*.war
+*.nar
+*.ear
+*.zip
+*.tar.gz
+*.rar
+
+# virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml
+hs_err_pid*
+replay_pid*
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### PyCharm ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm Patch ###
+# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
+
+# *.iml
+# modules.xml
+# .idea/misc.xml
+# *.ipr
+
+# Sonarlint plugin
+# https://plugins.jetbrains.com/plugin/7973-sonarlint
+.idea/**/sonarlint/
+
+# SonarQube Plugin
+# https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin
+.idea/**/sonarIssues.xml
+
+# Markdown Navigator plugin
+# https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced
+.idea/**/markdown-navigator.xml
+.idea/**/markdown-navigator-enh.xml
+.idea/**/markdown-navigator/
+
+# Cache file creation bug
+# See https://youtrack.jetbrains.com/issue/JBR-2257
+.idea/$CACHE_FILE$
+
+# CodeStream plugin
+# https://plugins.jetbrains.com/plugin/12206-codestream
+.idea/codestream.xml
+
+# Azure Toolkit for IntelliJ plugin
+# https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij
+.idea/**/azureSettings.xml
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.toptal.com/developers/gitignore/api/python,java,c++,pycharm,visualstudiocode,macos,linux,windows
+
+.*
+flow_modules/

ChatHumanFlowModule.py

@@ -0,0 +1,55 @@
+from flows.base_flows import CircularFlow
+from flows.utils import logging
+
+log = logging.get_logger(f"flows.{__name__}")
+
+
+class ChatHumanFlowModule(CircularFlow):
+    """ This class implements a Chat Human Flow Module. It is a flow that consists of two sub-flows that are executed circularly. It Contains the following subflows:
+    
+    - A User Flow: A flow makes queries to the Assistant Flow. E.g. The user asks the assistant (LLM) a question.
+    - A Assistant Flow: A flow that responds to queries made by the User Flow. E.g. The assistant (LLM) answers the user's question.
+    
+    To end the interaction, the user must type "\<END\>"
+    
+    An illustration of the flow is as follows:
+    
+            |------> User Flow -----------> |
+            ^                               |
+            |                               |
+            |                               v
+            |<------ Assistant Flow <-------|
+    
+    *Configuration Parameters*:
+    
+    - `name` (str): The name of the flow. Default: "ChatHumanFlowModule"
+    - `description` (str): A description of the flow. This description is used to generate the help message of the flow.
+    Default: "Flow that enables chatting between a ChatAtomicFlow and a user providing the input."
+    - `max_rounds` (int): The maximum number of rounds the flow can run for. Default: None, which means that there is no limit on the number of rounds.
+    - `early_exit_key` (str): The key that is used to exit the flow. Default: "end_of_interaction"
+    - `subflows_config` (Dict[str,Any]): A dictionary of subflows configurations. Default:
+        - `Assistant Flow`: The configuration of the Assistant Flow. By default, it a ChatAtomicFlow. It default parmaters are defined in ChatAtomicFlowModule.
+        - `User Flow`: The configuration of the User Flow. By default, it a HumanStandardInputFlow. It default parmaters are defined in HumanStandardInputFlowModule.
+    - `topology` (str): (List[Dict[str,Any]]): The topology of the flow which is "circular".
+    By default, the topology is the one shown in the illustration above (the topology is also described in ChatHumanFlowModule.yaml).
+
+    *Input Interface*:
+    
+    - None. By default, the input interface doesn't expect any input.
+        
+    *Output Interface*:
+
+    - `end_of_interaction` (bool): Whether the interaction is finished or not.
+    
+    :param \**kwargs: Arguments to be passed to the parent class CircularFlow constructor.
+    :type \**kwargs: Dict[str, Any]
+    """
+    
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    @classmethod
+    def type(cls):
+        """ This method returns the type of the flow."""
+        return "OpenAIChatHumanFlowModule"

ChatHumanFlowModule.yaml

@@ -0,0 +1,67 @@
+name: "ChatInteractiveFlow"
+description: "Flow that enables chatting between a ChatAtomicFlow and a user providing the input."
+
+max_rounds: null # Run until early exit is detected
+
+input_interface:
+  _target_: flows.interfaces.KeyInterface
+  
+output_interface:
+  - "end_of_interaction"
+  - "answer"
+
+subflows_config:
+  Assistant:
+    _target_: aiflows.ChatFlowModule.ChatAtomicFlow.instantiate_from_default_config
+  User:
+    _target_: aiflows.HumanStandardInputFlowModule.HumanStandardInputFlow.instantiate_from_default_config
+
+topology:
+  - goal: "Query the assistant"
+
+    ### Input Interface
+    input_interface:
+      _target_: flows.interfaces.KeyInterface
+      additional_transformations:
+        - _target_: flows.data_transformations.KeyMatchInput
+
+    ### Flow Specification
+    flow: Assistant
+    reset_every_round: false
+
+    ### Output Interface
+    output_interface:
+      _target_: flows.interfaces.KeyInterface
+      additional_transformations:
+        - _target_: flows.data_transformations.PrintPreviousMessages
+
+  - goal: "Ask the user for input"
+
+    ### Input Interface
+    input_interface:
+      _target_: flows.interfaces.KeyInterface
+      additional_transformations:
+        - _target_: flows.data_transformations.KeyMatchInput
+
+    ### Flow Specification
+    flow: User
+    reset_every_round: true
+
+    ### Output Interface
+    output_interface:
+      _target_: flows.interfaces.KeyInterface
+      keys_to_rename:
+        human_input: query
+      additional_transformations:
+        - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
+          regex: '(?<=```answer)([\s\S]*?)(?=```)'
+          input_key: "query"
+          output_key: "answer"
+          strip: True
+          assert_unique: True
+        - _target_: flows.data_transformations.EndOfInteraction
+          end_of_interaction_string: "<END>"
+          input_key: "query"
+          output_key: "end_of_interaction"
+
+early_exit_key: "end_of_interaction"

__init__.py

@@ -0,0 +1,11 @@
+# ~~~ Specify the dependencies ~~~
+dependencies = [
+    {"url": "aiflows/ChatFlowModule", "revision": "main"},
+    {"url": "aiflows/HumanStandardInputFlowModule", "revision": "main"},
+]
+from flows import flow_verse
+
+flow_verse.sync_dependencies(dependencies)
+# ~~~
+
+from .ChatHumanFlowModule import ChatHumanFlowModule

demo.yaml

@@ -0,0 +1,31 @@
+
+
+flow:
+  max_rounds: 5
+  _target_: aiflows.ChatInteractiveFlowModule.ChatHumanFlowModule.instantiate_from_default_config
+  subflows_config:
+    Assistant:
+      _target_: aiflows.ChatFlowModule.ChatAtomicFlow.instantiate_from_default_config
+      backend:
+        _target_: flows.backends.llm_lite.LiteLLMBackend
+        api_infos: ???
+        model_name: 
+          openai: "gpt-4"
+          azure: "azure/gpt-4"
+      input_interface_non_initialized: []
+      
+    User:
+      _target_: aiflows.HumanStandardInputFlowModule.HumanStandardInputFlow.instantiate_from_default_config
+      request_multi_line_input_flag: False
+      query_message_prompt_template: 
+        _target_: flows.prompt_template.JinjaPrompt
+        template: |2-
+          {{api_output}}
+          
+          To end an Interaction, type <END> and press enter.
+          
+        input_variables: ["api_output"]
+      input_interface:
+        - "api_output"
+      output_interface:
+        - "human_input"

run.py

@@ -0,0 +1,77 @@
+"""A simple script to run a Flow that can be used for development and debugging."""
+
+import os
+
+import hydra
+
+import flows
+from flows.flow_launchers import FlowLauncher
+from flows.backends.api_info import ApiInfo
+from flows.utils.general_helpers import read_yaml_file
+
+from flows import logging
+from flows.flow_cache import CACHING_PARAMETERS, clear_cache
+
+CACHING_PARAMETERS.do_caching = False  # Set to True to enable caching
+# clear_cache() # Uncomment this line to clear the cache
+
+logging.set_verbosity_debug()
+
+dependencies = [
+    {"url": "aiflows/ChatInteractiveFlowModule", "revision": os.getcwd()},
+]
+from flows import flow_verse
+flow_verse.sync_dependencies(dependencies)
+
+if __name__ == "__main__":
+    # ~~~ Set the API information ~~~
+    # OpenAI backend
+
+    api_information = [ApiInfo(backend_used="openai",
+                              api_key = os.getenv("OPENAI_API_KEY"))]
+    
+    
+    # # Azure backend
+    # api_information = ApiInfo(backend_used = "azure",
+    #                           api_base = os.getenv("AZURE_API_BASE"),
+    #                           api_key = os.getenv("AZURE_OPENAI_KEY"),
+    #                           api_version =  os.getenv("AZURE_API_VERSION") )
+
+    root_dir = "."
+    cfg_path = os.path.join(root_dir, "demo.yaml")
+    cfg = read_yaml_file(cfg_path)
+    
+    cfg["flow"]["subflows_config"]["Assistant"]["backend"]["api_infos"] = api_information
+    
+    # ~~~ Instantiate the Flow ~~~
+    flow_with_interfaces = {
+        "flow": hydra.utils.instantiate(cfg['flow'], _recursive_=False, _convert_="partial"),
+        "input_interface": (
+            None
+            if cfg.get( "input_interface", None) is None
+            else hydra.utils.instantiate(cfg['input_interface'], _recursive_=False)
+        ),
+        "output_interface": (
+            None
+            if cfg.get( "output_interface", None) is None
+            else hydra.utils.instantiate(cfg['output_interface'], _recursive_=False)
+        ),
+    }
+    # ~~~ Get the data ~~~
+    data = {"id": 0}  # This can be a list of samples
+    # data = {"id": 0, "question": "Who was the NBA champion in 2023?"}  # This can be a list of samples
+
+    # ~~~ Run inference ~~~
+    path_to_output_file = None
+    # path_to_output_file = "output.jsonl"  # Uncomment this line to save the output to disk
+
+    _, outputs = FlowLauncher.launch(
+        flow_with_interfaces=flow_with_interfaces,
+        data=data,
+        path_to_output_file=path_to_output_file
+    )
+
+    # ~~~ Print the output ~~~
+    flow_output_data = outputs[0]
+    print(flow_output_data)
+