Tips and Tricks¶

Command line tool¶

ParlAI comes with a "super" command, that has all the other commands built in:

$parlaihelp
ParlAI-DialogueResearchPlatform
usage:parlai[-h]COMMAND...
optionalarguments:
-h,--helpshowthishelpmessageandexit
Commands:
display_data(dd)Displaydatafromatask
display_model(dm)Displaymodelpredictions.
eval_model(em,eval)Evaluateamodel
train_model(tm,train)Trainamodel
interactive(i)Interactivechatwithamodelonthecommandline
safe_interactiveLikeinteractive,butaddsasafetyfilter
self_chatGenerateself-chatsofamodel

This is often more convenient than running the scripts from the examples directory.

This command also supports autocompletion of commands and options in your bash prompt. You can enable this by running

python--modelpipinstallargcomplete

and then adding the following line to your .bashrc or equivalent:

eval"$(register-python-argcompleteparlai)"

Multi-tasking with weighted tasks¶

If you want to train/eval/display with multiple tasks you can just use for example:

parlaidisplay_data--taskpersonachat,squad--datatypetrain

However, this will sample episodes equally from the two tasks (personachat and squad). To sample squad 10x more often you can do:

parlaidisplay_data--taskpersonachat,squad--multitask_weights1,10--datatypetrain

Tasks with Parameters¶

Some tasks have their own flags. While these can be separately added on the command line, especially when multi-tasking it is possible to group them with the task name itself. If you are using the same task, but with two different sets of parameters this is the only way that will work, otherwise the flags would be ambiguous and not associated with those tasks. This can be done on the command line in the following way:

parlaidisplay_data--tasklight_dialog:light_label_type=speech,light_dialog:light_label_type=emote--datatypetrain

That is, by adding a colon ":" followed by the flag name, an equals sign, and the value. You can add multiple flags, all separated by ":".

Agent Convenience Functions¶

Tip: Having implemented batch_act() and act(), you can make use of the agent convenience functions batch_respond() and respond() which provide the agent’s response to messages by internally calling batch_act() and act() respectively. The function signatures are as follows:

def respond(self, text_or_message: Union[str, Message], **other_message_fields) -> str:
 pass
def batch_respond(self, messages: List[Message]) -> List[str]:
 pass

Self-Chats¶

Sometimes it is useful to generate models talking to themselves. You can do this with:

# Self-chatting Poly-Encoder model on ConvAI2
parlaiself_chat--model-filezoo:pretrained_transformers/model_poly/model--taskconvai2--inferencetopk--num-self-chats10--display-examplesTrue--datatypevalid

This will generate 10 self-chats between 2 poly-encoder models with persona context data from convai2.

Flags to generate and store the self-chat:

• --num-self-chats specify the number of self-chats to generate (1 by default).

• --selfchat-max-turns specify the number of self-chat turns (6 by default), including context turn, seeded-utterance turns. Some self-chat world includes context information (such as persona; Wizard of Wikipedia(WoW) topics) in addition to the model utterances.

• --selfchat-task specify whether to create a self-chat version of the task. If True (by default), it allows for loading contexts and openers that seed the self-chat.

• --outfile specify file to save self-chat logs.

• --save-format specify the format to save self-chat logs in. Use conversations for jsonl format, or parlai for text format (conversations by default).

• --partner-model-file allows self-chat to be performed between two different models. If so, set this flag to one model and -mf for the second one.

• --partner-opt-file use this to define an opt file containing args to override for --partner_model_file.

Self-Chat World

If the self-chat needs additional context to start with, e.g. persona, topics, one can specify it with -t <task_name> (in the above case "convai2") which links to a ParlAI world in the task world module parlai.tasks.{task_name}.worlds that handles the particular nature of interactions, e.g. here or here.

The base SelfChatWorld consists of:

• contexts specify context information such as persona, topics, sometimes initial utterances.

• _opener consists of seeded messages from the task.

• parley() handles the logic of two agents interacting with each other with additional seeded contexts and/or utterances.

Flags for setting up the SelfChatWorld:

• -t: name of the self-chat task.

• --seed-messages-from-task: whether to seed the self-chat with first utterances from the task dataset with specified datatype (train:evalmode by default).

:::{warning} WARNING To initialize a list of openers to seed the self-chat, the default method of init_openers goes through each episode of the task dataset and extract the first dialogue turn, which might itself contain context information, such as persona, in addition to the first dialogue messages. :::

Additional flags for setting up the task-specific SelfChatWorld, e.g. for Blended Skill Talk (BST) self-chat:

• --include-personas: if True (by default), it will prepend the persona strings to the context each agent observes before the self-chat begins.

• --include-initial-utterances: if True (by default), it will prepend the initial utterances to the context each agent observes before the self-chat begins. For example, the self-chats evaluated in the BlenderBot paper were generated by

parlaiself_chat--model-filezoo:blender/blender_90M/model--taskblended_skill_talk--datatypevalid--num-self-chats200

which output 200 self-chats where each agent observe its own persona, a shared WoW topic if any and initial utterances from a BST episode.

If the model does not need to run on a particular task you can also use:

# Self-chatting Poly-Encoder model on a generic task (so e.g., no ConvAI2 personas are input)
parlaiself_chat--model-filezoo:pretrained_transformers/model_poly/model--inferencetopk--num-self-chats10--display-examplesTrue

Prettifying Display of Chats¶

This handy script can prettify the display of json file of chats (sequences of parlai messages):

# Display conversation in HTML format.
pythonparlai/scripts/convo_render.py-iprojects/wizard_of_wikipedia/chat_example1.jsonl-o/tmp/chat.html

Some additional flags that can be used for convo-render:

• --num-examples the number of conversations to render from the json file (10 by default).

Internal Agents, Tasks and More¶

You can create a private folder in ParlAI with your own custom agents and tasks, create your own model zoo, and manage it all with a separate git repository.

For more detailed instructions and features, see the README