coflows working version

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.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/

ChatWithDemonstrationsFlow.py

@@ -0,0 +1,78 @@
+
+
+from aiflows.base_flows import CompositeFlow
+from aiflows.utils import logging
+from aiflows.interfaces import KeyInterface
+logging.set_verbosity_debug()
+
+log = logging.get_logger(__name__)
+
+
+class ChatWithDemonstrationsFlow(CompositeFlow):
+    """ A Chat with Demonstrations Flow. It is a flow that consists of multiple sub-flows that are executed sequentially.
+    It's parent class is SequentialFlow.
+    
+        It Contains the following subflows:
+            - A Demonstration Flow: It is a flow that passes demonstrations to the ChatFlow
+            - A Chat Flow: It is a flow that uses the demonstrations to answer queries asked by the user/human.
+        
+    An illustration of the flow is as follows:
+        
+                -------> Demonstration Flow -------> Chat Flow ------->
+                
+    *Configuration Parameters*:
+        
+    - `name` (str): The name of the flow. Default: "ChatAtomic_Flow_with_Demonstrations"
+    - `description` (str): A description of the flow. This description is used to generate the help message of the flow.
+    Default:  "A sequential flow that answers questions with demonstrations"
+    - `subflows_config` (Dict[str,Any]): A dictionary of subflows configurations of the sequential Flow. Default:
+        - `Demonstration Flow`: The configuration of the Demonstration Flow. By default, it a DemonstrationsAtomicFlow.
+        Its default parmaters are defined in DemonstrationsAtomicFlow).
+        - `Chat Flow`: The configuration of the Chat Flow. By default, its a ChatAtomicFlow.
+        Its default parmaters are defined in ChatAtomicFlowModule (see Flowcard, i.e. README.md, of ChatAtomicFlowModule).
+    - `topology` (str): The topology of the flow which is "sequential".  By default, the topology is the one shown in the
+    illustration above (the topology is also described in ChatWithDemonstrationsFlow.yaml).
+                
+    *Input Interface*:
+    
+    - `query` (str): A query asked to the flow (e.g. "What is the capital of France?")
+    
+    Output Interface:
+
+    - `answer` (str): The answer of the flow to the query
+        
+    :param \**kwargs: Arguments to be passed to the parent class SequentialFlow constructor.
+    """
+    def __init__(self,**kwargs):
+        super().__init__(**kwargs)
+        self.output_interface = KeyInterface(
+            keys_to_rename={"api_output": "answer"}
+        )
+
+    def set_up_flow_state(self):
+        super().set_up_flow_state()
+        self.flow_state["last_flow_called"] = None
+            
+    def run(self,input_data):
+        
+        #~~~~~~~~~~~Solution 1 - Blocking ~~~~~~~
+        future = self.ask_subflow("demonstration_flow",input_data)
+        
+        answer = self.ask_subflow("chat_flow",future.get_data())
+        return self.output_interface(answer.get_data())
+        
+        # #~~~~~~~~~~~Solution 2 - Non-Blocking ~~~~~~~
+        # if self.flow_state["last_flow_called"] is None:
+        #     self.ask_pipe_subflow("demonstration_flow",input_data)
+        #     self.flow_state["last_flow_called"] = "demonstration_flow"
+        #     return {"answer": "Just Called the Demonstration Flow"}
+        
+        # elif self.flow_state["last_flow_called"] == "demonstration_flow":
+        #     self.ask_pipe_subflow("chat_flow",input_data)
+        #     self.flow_state["last_flow_called"] = "chat_flow"
+        #     return {"answer": "Just Called the Demonstration Flow"}
+        
+        # self.flow_state["last_flow_called"] = None
+        return self.output_interface(input_data)
+        
+       

ChatWithDemonstrationsFlow.yaml

@@ -0,0 +1,13 @@
+
+name: "ChatAtomic_Flow_with_Demonstrations"
+description: "A sequential flow that answers questions with demonstrations"
+
+subflows_config:
+  demonstration_flow:
+    _target_: flow_modules.aiflows.ChatWithDemonstrationsFlowModule.DemonstrationsAtomicFlow.instantiate_from_default_config
+    name: "DemonstrationsAtomicFlow"
+    description: "A flow that answers questions with demonstrations"
+  chat_flow:
+    _target_: flow_modules.aiflows.ChatFlowModule.ChatAtomicFlow.instantiate_from_default_config
+    name: "ChatAtomicFlow"
+    description: "A flow that answers questions"

DemonstrationsAtomicFlow.py

@@ -0,0 +1,193 @@
+import jinja2
+from aiflows.base_flows import AtomicFlow
+from aiflows.utils import logging
+from aiflows.utils import general_helpers
+from typing import Dict,Any,Optional,List
+from aiflows.prompt_template import JinjaPrompt
+from copy import deepcopy
+import os
+import hydra
+log = logging.get_logger(__name__)
+
+class DemonstrationsAtomicFlow(AtomicFlow):
+    """ This class implements a Demonstrations Atomic Flow. It is a flow which is usually used to pass demonstrations (of user assistant interactions)
+    to the ChatAtomicFlow.
+    
+    *Configuration Parameters*:
+    
+    - `name` (str): The name of the flow. Default: "DemonstrationsAtomicFlow"
+    - `description` (str): A description of the flow. This description is used to generate the help message of the flow.
+    Default: "A flow that passes demonstrations to the ChatFlow"
+    - `data` (List[Dict[str, Any]]): The data of the demonstrations.
+    If data is None, the data is loaded from the file specified in the params["data_dir"].
+    Default: No default value this field must be set.
+    - `params` (Dict[str, Any]): The parameters specific to the dataset of the demonstrations. Its default parameters are:
+        - `data_dir` (str): The directory where the demonstrations are stored. If the data is not directly passed to the flow through `data` then
+        the data is loaded from this directory. Default: No default value this field must be set.
+        - `demonstrations_id` (str): The id of the demonstrations (name of the data file). If the data is not directly passed to the flow through `data` then
+        the data is loaded from this file. Default: No default value this field must be set.
+        - `demonstrations_k` (int): The number of demonstrations to pass to the ChatFlow.
+        If None, all the demonstrations are passed to the ChatFlow. Default: None
+    - `query_prompt_template` (Dict[str, Any]): The prompt template used to generate the query of the demonstrations. 
+    By default its of type flows.prompt_template.JinjaPrompt. None of the parameters of the prompt are defined by default and therefore need to be defined if one
+    wants to use the query_prompt_template. Default parameters are defined in flows.prompt_template.jinja2_prompts.JinjaPrompt.
+    - `response_prompt_template` (Dict[str, Any]): The prompt template used to generate the response of the demonstrations. By default its of type flows.prompt_template.JinjaPrompt.
+    None of the parameters of the prompt are defined by default and therefore need to be defined if one
+    wants to use the response_prompt_template. Default parameters are defined in flows.prompt_template.jinja2_prompts.JinjaPrompt.
+
+    *Input Interface*:
+    
+    - The input interface expected by its successor flow (e.g. typically ChatAtomicFlow so the input interface is the one expected by ChatAtomicFlow)
+        
+    *Output Interface*:
+
+    - The input interface expected by its successor flow (e.g. typically ChatAtomicFlow so the input interface expected by ChatAtomicFlow))
+    - `demonstrations` (List[Dict[str, Any]]): A list of demonstrations. Each demonstration is a dictionary with the following keys:
+                                                    - idx (int): The index of the demonstration
+                                                    - query (str): The query of the demonstration
+                                                    - response (str): The response of the demonstration
+        
+    :param params: The parameters specific to the dataset of the demonstrations. It must sould contain the following keys:
+                        - 'data_dir' (str): The directory where the demonstrations are stored. This field is used if the data is not directly passed to the flow through the 'data' field.
+                        - 'demonstrations_id' (str): The id of the demonstrations (name of the data file). This field is used if the data is not directly passed to the flow through the 'data' field.
+                        - 'demonstrations_k' (int): The number of demonstrations to pass to the ChatFlow. If None, all the demonstrations are passed to the ChatFlow.
+                        - 'ids_to_keep' (Optional[Union[str, List[str]]]): The ids of the demonstrations to keep. If None, all the demonstrations are kept.
+    :type params: Dict[str, Any]
+    :param query_prompt_template: The prompt template used to generate the query of the demonstrations.
+    :type query_prompt_template: JinjaPrompt
+    :param response_prompt_template: The prompt template used to generate the response of the demonstrations.
+    :type response_prompt_template: JinjaPrompt
+    :param data: The data of the demonstrations. If None, the data is loaded from the file specified in the params.
+    :type data: Optional[List[Dict[str, Any]]]
+    """
+    demonstrations_k: Optional[int] = None
+    query_prompt_template: JinjaPrompt
+    response_prompt_template: JinjaPrompt
+    params: Dict
+    
+    def __init__(self,params,query_prompt_template,response_prompt_template, data=None,**kwargs):
+        super().__init__(**kwargs)
+        self.params = params
+        self.data = data
+        self.demonstrations_k = self.params.get("demonstrations_k", None)
+        
+        #typically the query would be what the user (human) asks the assistant (LLM) 
+        self.query_prompt_template = query_prompt_template
+        #typically the response would be what the assistant (LLM) should answer to the user (human) 
+        self.response_prompt_template = response_prompt_template
+        if self.data is None:
+            self._load_data()
+            
+    @classmethod
+    def _set_up_prompts(cls, config):
+        """ This method instantiates the prompt templates of the flow (used when instantiating the flow from a config file)
+        
+            :param config: The configuration of the flow.
+            :type config: Dict[str, Any]
+            :return: A dictionary of keyword arguments to pass to the constructor of the flow.
+            :rtype: Dict[str, Any]
+        """
+        kwargs = {}
+        kwargs["query_prompt_template"] = \
+            hydra.utils.instantiate(config['query_prompt_template'], _convert_="partial")
+        kwargs["response_prompt_template"] = \
+            hydra.utils.instantiate(config['response_prompt_template'], _convert_="partial")
+        return kwargs
+        
+    @classmethod
+    def instantiate_from_config(cls, config):
+        """ This method instantiates the flow from a config file. 
+        
+        :param config: The configuration of the flow.
+        :type config: Dict[str, Any]
+        :return: The instantiated flow.
+        :rtype: Flow
+        """
+        flow_config = deepcopy(config)
+
+        kwargs = {"flow_config": flow_config}
+
+        # ~~~ Set up prompts ~~~
+        kwargs.update(cls._set_up_prompts(flow_config))
+        kwargs.update({"params": flow_config["params"]})
+        kwargs.update({"data": flow_config["data"]})
+        # ~~~ Instantiate flow ~~~
+        return cls(**kwargs)
+            
+    def _get_query_message_content(self, sample_data: Dict):
+        """ This method returns the query message content of a demonstration given the sample data (by rendering the query prompt template).
+        
+        :param sample_data: The sample data of the demonstration.
+        :type sample_data: Dict[str, Any]
+        :return: The query message content of the demonstration.
+        :rtype: str
+        """
+        input_variables = self.query_prompt_template.input_variables
+        return self.query_prompt_template.format(**{k: sample_data[k] for k in input_variables})
+
+    def _get_response_message_content(self, sample_data: Dict):
+        """ This method returns the response message content of a demonstration given the sample data (by rendering the response prompt template).
+        
+        :param sample_data: The sample data of the demonstration.
+        :type sample_data: Dict[str, Any]
+        :return: The response message content of the demonstration.
+        :rtype: str
+        """
+        input_variables = self.response_prompt_template.input_variables
+        return self.response_prompt_template.format(**{k: sample_data[k] for k in input_variables})
+        
+    def _get_io_pair(self, idx):
+        """ This method, given the index of a demonstration, returns an query-response pair from the demonstrations data.
+        
+        :param idx: The index of the demonstration.
+        :type idx: int
+        :return: The query-response pair at idx from the demonstrations data.
+        :rtype: Dict[str, Any]
+        """
+        dp = self.data[idx]
+        
+        query_data = dp["query_data"]
+        response_data = dp["response_data"]
+        
+        query = self._get_query_message_content(query_data)
+        response = self._get_response_message_content(response_data)
+        
+        return {"idx": idx, "query": query,"response": response}
+            
+    def _get_io_pairs(self,input_data: Dict[str, Any]) -> List[Any]:
+        """ This method returns the demonstrations that are passed to the destination flow (typically ChatAtomicFlow).
+        
+        :param input_data: The input data of the flow.
+        :type input_data: Dict[str, Any]
+        :return: The demonstrations that are passed to the destination flow.
+        :rtype: List[Any]
+        """
+        demonstrations_k = self.demonstrations_k if self.demonstrations_k is not None else len(self.data)
+        io_pairs = [self._get_io_pair(idx) for idx in range(demonstrations_k)]
+        return io_pairs
+        
+    def _load_data(self):
+        """ This method loads the demonstrations from the file specified in the params. It also filters the demonstrations if the ids_to_keep parameter is specified."""
+        demonstrations_file = os.path.join(self.params["data_dir"], f"{self.params['demonstrations_id']}.jsonl")
+        self.data = general_helpers.read_jsonlines(demonstrations_file)
+        
+        if self.params.get("ids_to_keep", False):
+            if isinstance(self.params["ids_to_keep"], str):
+                ids_to_keep = set(self.params["ids_to_keep"].split(","))
+            else:
+                ids_to_keep = set(self.params["ids_to_keep"])
+
+            self.data = [d for d in self.data if d["id"] in ids_to_keep]
+
+        log.info("Loaded the demonstrations for %d datapoints from %s", len(self.data), self.params["data_dir"])
+
+    def run(self,
+            input_data: Dict[str, Any]) -> Dict[str, Any]:
+        """ This method runs the flow. It returns the input data of the flow with the demonstrations added to it.
+        
+        :param input_data: The input data of the flow.
+        :type input_data: Dict[str, Any]
+        :return: The input data of the flow with the demonstrations added to it.
+        :rtype: Dict[str, Any]
+        """
+        return {**input_data,**{"demonstrations": self._get_io_pairs(input_data=input_data)}}

DemonstrationsAtomicFlow.yaml

@@ -0,0 +1,15 @@
+name: "DemonstrationAtomicFlow"
+description: "A flow which returns Demonstrations"
+
+data: ??? #e.g. [{"query_data": {"query": "What is the capital of France?"}, "response_data": {"response": "Paris, my sir."}}]
+params:
+  data_dir: ???
+  demonstrations_id: ??? 
+  ids_to_keep: null
+  demonstrations_k: null
+
+query_prompt_template:
+  _target_: aiflows.prompt_template.JinjaPrompt
+
+response_prompt_template:
+  _target_: aiflows.prompt_template.JinjaPrompt

README.md

@@ -0,0 +1,165 @@
+---
+license: mit
+---
+
+# Table of Contents
+
+* [\_\_init\_\_](#__init__)
+* [DemonstrationsAtomicFlow](#DemonstrationsAtomicFlow)
+  * [DemonstrationsAtomicFlow](#DemonstrationsAtomicFlow.DemonstrationsAtomicFlow)
+    * [instantiate\_from\_config](#DemonstrationsAtomicFlow.DemonstrationsAtomicFlow.instantiate_from_config)
+    * [run](#DemonstrationsAtomicFlow.DemonstrationsAtomicFlow.run)
+* [ChatWithDemonstrationsFlow](#ChatWithDemonstrationsFlow)
+  * [ChatWithDemonstrationsFlow](#ChatWithDemonstrationsFlow.ChatWithDemonstrationsFlow)
+
+<a id="__init__"></a>
+
+# \_\_init\_\_
+
+<a id="DemonstrationsAtomicFlow"></a>
+
+# DemonstrationsAtomicFlow
+
+<a id="DemonstrationsAtomicFlow.DemonstrationsAtomicFlow"></a>
+
+## DemonstrationsAtomicFlow Objects
+
+```python
+class DemonstrationsAtomicFlow(AtomicFlow)
+```
+
+This class implements a Demonstrations Atomic Flow. It is a flow which is usually used to pass demonstrations (of user assistant interactions)
+
+to the ChatAtomicFlow.
+
+*Configuration Parameters*:
+
+- `name` (str): The name of the flow. Default: "DemonstrationsAtomicFlow"
+- `description` (str): A description of the flow. This description is used to generate the help message of the flow.
+Default: "A flow that passes demonstrations to the ChatFlow"
+- `data` (List[Dict[str, Any]]): The data of the demonstrations.
+If data is None, the data is loaded from the file specified in the params["data_dir"].
+Default: No default value this field must be set.
+- `params` (Dict[str, Any]): The parameters specific to the dataset of the demonstrations. Its default parameters are:
+    - `data_dir` (str): The directory where the demonstrations are stored. If the data is not directly passed to the flow through `data` then
+    the data is loaded from this directory. Default: No default value this field must be set.
+    - `demonstrations_id` (str): The id of the demonstrations (name of the data file). If the data is not directly passed to the flow through `data` then
+    the data is loaded from this file. Default: No default value this field must be set.
+    - `demonstrations_k` (int): The number of demonstrations to pass to the ChatFlow.
+    If None, all the demonstrations are passed to the ChatFlow. Default: None
+- `query_prompt_template` (Dict[str, Any]): The prompt template used to generate the query of the demonstrations. 
+By default its of type aiflows.prompt_template.JinjaPrompt. None of the parameters of the prompt are defined by default and therefore need to be defined if one
+wants to use the query_prompt_template. Default parameters are defined in aiflows.prompt_template.jinja2_prompts.JinjaPrompt.
+- `response_prompt_template` (Dict[str, Any]): The prompt template used to generate the response of the demonstrations. By default its of type aiflows.prompt_template.JinjaPrompt.
+None of the parameters of the prompt are defined by default and therefore need to be defined if one
+wants to use the response_prompt_template. Default parameters are defined in aiflows.prompt_template.jinja2_prompts.JinjaPrompt.
+
+*Input Interface*:
+
+- The input interface expected by its successor flow (e.g. typically ChatAtomicFlow so the input interface is the one expected by ChatAtomicFlow)
+
+*Output Interface*:
+
+- The input interface expected by its successor flow (e.g. typically ChatAtomicFlow so the input interface expected by ChatAtomicFlow))
+- `demonstrations` (List[Dict[str, Any]]): A list of demonstrations. Each demonstration is a dictionary with the following keys:
+                                                - idx (int): The index of the demonstration
+                                                - query (str): The query of the demonstration
+                                                - response (str): The response of the demonstration
+
+**Arguments**:
+
+- `params` (`Dict[str, Any]`): The parameters specific to the dataset of the demonstrations. It must sould contain the following keys:
+- 'data_dir' (str): The directory where the demonstrations are stored. This field is used if the data is not directly passed to the flow through the 'data' field.
+- 'demonstrations_id' (str): The id of the demonstrations (name of the data file). This field is used if the data is not directly passed to the flow through the 'data' field.
+- 'demonstrations_k' (int): The number of demonstrations to pass to the ChatFlow. If None, all the demonstrations are passed to the ChatFlow.
+- 'ids_to_keep' (Optional[Union[str, List[str]]]): The ids of the demonstrations to keep. If None, all the demonstrations are kept.
+- `query_prompt_template` (`JinjaPrompt`): The prompt template used to generate the query of the demonstrations.
+- `response_prompt_template` (`JinjaPrompt`): The prompt template used to generate the response of the demonstrations.
+- `data` (`Optional[List[Dict[str, Any]]]`): The data of the demonstrations. If None, the data is loaded from the file specified in the params.
+
+<a id="DemonstrationsAtomicFlow.DemonstrationsAtomicFlow.instantiate_from_config"></a>
+
+#### instantiate\_from\_config
+
+```python
+@classmethod
+def instantiate_from_config(cls, config)
+```
+
+This method instantiates the flow from a config file.
+
+**Arguments**:
+
+- `config` (`Dict[str, Any]`): The configuration of the flow.
+
+**Returns**:
+
+`Flow`: The instantiated flow.
+
+<a id="DemonstrationsAtomicFlow.DemonstrationsAtomicFlow.run"></a>
+
+#### run
+
+```python
+def run(input_data: Dict[str, Any]) -> Dict[str, Any]
+```
+
+This method runs the flow. It returns the input data of the flow with the demonstrations added to it.
+
+**Arguments**:
+
+- `input_data` (`Dict[str, Any]`): The input data of the flow.
+
+**Returns**:
+
+`Dict[str, Any]`: The input data of the flow with the demonstrations added to it.
+
+<a id="ChatWithDemonstrationsFlow"></a>
+
+# ChatWithDemonstrationsFlow
+
+<a id="ChatWithDemonstrationsFlow.ChatWithDemonstrationsFlow"></a>
+
+## ChatWithDemonstrationsFlow Objects
+
+```python
+class ChatWithDemonstrationsFlow(SequentialFlow)
+```
+
+A Chat with Demonstrations Flow. It is a flow that consists of multiple sub-flows that are executed sequentially.
+
+It's parent class is SequentialFlow.
+
+    It Contains the following subflows:
+        - A Demonstration Flow: It is a flow that passes demonstrations to the ChatFlow
+        - A Chat Flow: It is a flow that uses the demonstrations to answer queries asked by the user/human.
+
+An illustration of the flow is as follows:
+
+            -------> Demonstration Flow -------> Chat Flow ------->
+
+*Configuration Parameters*:
+
+- `name` (str): The name of the flow. Default: "ChatAtomic_Flow_with_Demonstrations"
+- `description` (str): A description of the flow. This description is used to generate the help message of the flow.
+Default:  "A sequential flow that answers questions with demonstrations"
+- `subflows_config` (Dict[str,Any]): A dictionary of subflows configurations of the sequential Flow. Default:
+    - `Demonstration Flow`: The configuration of the Demonstration Flow. By default, it a DemonstrationsAtomicFlow.
+    Its default parmaters are defined in DemonstrationsAtomicFlow).
+    - `Chat Flow`: The configuration of the Chat Flow. By default, its a ChatAtomicFlow.
+    Its default parmaters are defined in ChatAtomicFlowModule (see Flowcard, i.e. README.md, of ChatAtomicFlowModule).
+- `topology` (str): The topology of the flow which is "sequential".  By default, the topology is the one shown in the
+illustration above (the topology is also described in ChatWithDemonstrationsFlow.yaml).
+
+*Input Interface*:
+
+- `query` (str): A query asked to the flow (e.g. "What is the capital of France?")
+
+Output Interface:
+
+- `answer` (str): The answer of the flow to the query
+
+**Arguments**:
+
+- `\**kwargs`: Arguments to be passed to the parent class SequentialFlow constructor.
+

__init__.py

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

demo.yaml

@@ -0,0 +1,73 @@
+_target_: flow_modules.aiflows.ChatWithDemonstrationsFlowModule.ChatWithDemonstrationsFlow.instantiate_from_default_config
+name: "SimpleQA_Flow_with_Demonstrations"
+description: "A sequential flow that answers questions with demonstrations"
+
+input_interface: # Connector between the "input data" and the Flow
+  - "questions"
+output_interface: # Connector between the Flow's output and the caller
+  - "answer"
+
+subflows_config:
+  demonstration_flow:
+    _target_: flow_modules.aiflows.ChatWithDemonstrationsFlowModule.DemonstrationsAtomicFlow.instantiate_from_default_config
+    data: 
+      - query_data:
+          query: "What is the capital of Turkey?"
+        response_data:
+          response: "Istambul, my sir."
+      - query_data:
+          query: "what is the capital of Germany?"
+        response_data:
+          response: "Berlin, my sir."
+    query_prompt_template:
+      template: |2-
+        Answer the following question: {{query}}
+      input_variables:
+        - "query"
+    response_prompt_template:
+      template: |2-
+        {{response}}
+      input_variables:
+        - response
+
+  chat_flow:
+    _target_: flow_modules.aiflows.ChatFlowModule.ChatAtomicFlow.instantiate_from_default_config
+    name: "SimpleQA_Flow"
+    # ~~~ Input interface specification ~~~
+    input_interface_non_initialized:
+      - "question"
+
+    # ~~~ backend model parameters ~~
+    backend:
+      _target_: aiflows.backends.llm_lite.LiteLLMBackend
+      api_infos: ???
+      model_name:
+        openai: "gpt-3.5-turbo"
+        azure: "azure/gpt-4"
+
+      # ~~~ generation_parameters ~~
+      n: 1
+      max_tokens: 3000
+      temperature: 0.3
+
+      top_p: 0.2
+      frequency_penalty: 0
+      presence_penalty: 0
+
+    n_api_retries: 6
+    wait_time_between_retries: 20
+
+    # ~~~ Prompt specification ~~~
+    system_message_prompt_template:
+      _target_: aiflows.prompt_template.JinjaPrompt
+      template: |2-
+        You are a helpful chatbot that truthfully answers questions. Answer in a similar way to your previous replies.
+      input_variables: []
+      partial_variables: {}
+
+    init_human_message_prompt_template:
+      _target_: aiflows.prompt_template.JinjaPrompt
+      template: |2-
+        Answer the following question: {{question}}
+      input_variables: ["question"]
+      partial_variables: {}

run.py

@@ -0,0 +1,90 @@
+import os
+
+import hydra
+
+import aiflows
+from aiflows.flow_launchers import FlowLauncher
+from aiflows.backends.api_info import ApiInfo
+from aiflows.utils.general_helpers import read_yaml_file, quick_load_api_keys
+
+from aiflows import logging
+from aiflows.flow_cache import CACHING_PARAMETERS, clear_cache
+from aiflows.utils import serve_utils
+from aiflows.workers import run_dispatch_worker_thread
+from aiflows.messages import FlowMessage
+from aiflows.interfaces import KeyInterface
+CACHING_PARAMETERS.do_caching = False  # Set to True in order to disable caching
+# clear_cache() # Uncomment this line to clear the cache
+
+logging.set_verbosity_debug()  # Uncomment this line to see verbose logs
+
+from aiflows import flow_verse
+
+
+dependencies = [
+    {"url": "aiflows/ChatWithDemonstrationsFlowModule", "revision": os.getcwd()}
+]
+
+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"))]
+
+
+    FLOW_MODULES_PATH = "./"
+    
+    jwt = os.getenv("COLINK_JWT")
+    addr = os.getenv("LOCAL_COLINK_ADDRESS")
+    
+    cl = serve_utils.start_colink_component(
+        "Reverse Number Demo",
+        {"jwt": jwt, "addr": addr}
+    )
+
+    # # 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)
+
+    serve_utils.recursive_serve_flow(
+        cl = cl,
+        flow_type="simpleDemonstrationQA",
+        default_config=cfg,
+        default_state=None,
+        default_dispatch_point="coflows_dispatch",
+    )
+    
+    quick_load_api_keys(cfg, api_information, key="api_infos")
+    
+    proxy_flow = serve_utils.recursive_mount(
+        cl=cl,
+        client_id="local",
+        flow_type="simpleDemonstrationQA",
+        config_overrides=cfg,
+        initial_state=None,
+        dispatch_point_override=None,
+    )   
+    
+    
+    # ~~~ Get the data ~~~
+    data = {"id": 0, "question": "What's the capital of France?"}  # 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 ~~~
+   
+    input_message = FlowMessage(
+        data= data,
+        src_flow="Coflows team",
+        dst_flow=proxy_flow,
+        is_input_msg=True
+    )
+    
+    future = proxy_flow.ask(input_message)
+    
+    print(future.get_data())