diff --git a/CHANGELOG.mdx b/CHANGELOG.mdx index f6e7b7405cc9..bb5e57de5c7f 100644 --- a/CHANGELOG.mdx +++ b/CHANGELOG.mdx @@ -16,6 +16,13 @@ https://github.com/RasaHQ/rasa/tree/main/changelog/ . --> +## [3.5.10] - 2023-05-23 + +Rasa 3.5.10 (2023-05-23) +### Improved Documentation +- [#12437](https://github.com/rasahq/rasa/issues/12437): Added documentation for spaces alpha + + ## [3.5.9] - 2023-05-19 Rasa 3.5.9 (2023-05-19) diff --git a/changelog/12437.doc.md b/changelog/12437.doc.md deleted file mode 100644 index 3640e5e02a75..000000000000 --- a/changelog/12437.doc.md +++ /dev/null @@ -1 +0,0 @@ -Added documentation for spaces alpha \ No newline at end of file diff --git a/docs/docs/glossary.mdx b/docs/docs/glossary.mdx index 86a116c24a49..4e817579751b 100644 --- a/docs/docs/glossary.mdx +++ b/docs/docs/glossary.mdx @@ -8,15 +8,15 @@ description: Glossary for all Rasa-related terms ## [Action](./actions.mdx) A single step that a bot takes in a conversation (e.g. calling an API or sending a response back to the user). - + ## [Action Server](https://rasa.com/docs/action-server/) - The server that runs custom action code, separate from Rasa. Rasa maintains the Rasa SDK in Python for implementing custom actions, although it's also possible to write custom actions in other languages. - + The server that runs custom action code, separate from Rasa. Rasa maintains the Rasa SDK in Python for implementing custom actions, although it's also possible to write custom actions in other languages. + ## Annotation Adding labels to messages and conversations so that they can be used to train a model. - + ## [Business Logic](./business-logic.mdx) Conditions that need to be fulfilled due to business requirements. For example: requiring a first and last name, an address, and a password before an account can be created. In a Rasa assistant, business logic is implemented using rule-based actions like [forms](./forms.mdx). @@ -30,11 +30,11 @@ description: Glossary for all Rasa-related terms ## CMS A way to store bot responses externally instead of including them directly in the domain. Content Management Systems decouple response text from training data. For more information, see [NLG Servers](./nlg.mdx). - + ## [Conversation-Driven Development (CDD)](./conversation-driven-development.mdx) The process of using user messages and conversation data to influence the design of an assistant and train the model, combined with engineering best practices. There are 6 steps that make up CDD: Share, Review, Annotate, Fix, Track, and Test. - + ## [Conversation Tests](./testing-your-assistant.mdx) Modified story format that includes the full text of the user message in addition to the intent label. Test conversations are saved to a test set file (conversation_tests.md), which is used to evaluate the model’s predictions across an entire conversation. @@ -98,7 +98,7 @@ Dual Intent and Entity Transformer. The default NLU architecture used by Rasa, w ## [Interactive Learning](./writing-stories.mdx#using-interactive-learning) In the Rasa CLI, a training mode where the developer corrects and validates the assistant’s predictions at every step of the conversation. The conversation can be saved to the story format and added to the assistant’s training data. - + ## [Knowledge Base / Knowledge Graph](https://rasa.com/docs/action-server/knowledge-bases) A queryable database that represents complex relationships and hierarchies between objects. Knowledge Base Actions allow Rasa to fetch information from a knowledge base and use it in responses. @@ -120,10 +120,10 @@ Dual Intent and Entity Transformer. The default NLU architecture used by Rasa, w Natural Language Generation (NLG) is the process of generating natural language messages to send to a user. Rasa uses a simple template-based approach for NLG. Data-driven approaches (such as neural NLG) can be implemented by creating a custom NLG component. - + ## [NLU](./nlu-training-data.mdx) - Natural Language Understanding (NLU) deals with parsing and understanding human language into a structured format. + Natural Language Understanding (NLU) deals with parsing and understanding human language into a structured format. ## [Pipeline](./tuning-your-model.mdx) @@ -136,27 +136,27 @@ Dual Intent and Entity Transformer. The default NLU architecture used by Rasa, w ## Rasa Core (Outdated - Rasa Core and Rasa NLU were merged into one package in 1.x. The functionality of Core is now referred to as dialogue management) - + The dialogue engine that decides what to do next in a conversation based on the context. Part of the Rasa library. ## Rasa NLU (Outdated - Rasa Core and Rasa NLU were merged into one package in 1.x. The functionality of Rasa NLU is now referred to as NLU) - + Rasa NLU is the part of Rasa that performs Natural Language Understanding ([NLU](#nlu)), including intent classification and entity extraction. ## [NLU Component](./components.mdx) An element in the Rasa NLU pipeline (see [Pipeline](#pipeline)) that processes incoming messages. Components perform tasks ranging from entity extraction to intent classification to pre-processing. - + ## [Rasa X/Enterprise](https://rasa.com/docs/rasa-enterprise/) A tool for [conversation-driven development](./conversation-driven-development.mdx). Rasa X/Enterprise helps teams share and test an assistant built with Rasa, annotate user messages, and view conversations. - + ## [Retrieval Intent](./chitchat-faqs.mdx) A special type of intent that can be divided into smaller sub-intents. For example, an FAQ retrieval intent has sub-intents that represent each individual question the assistant knows how to answer. - + ## [REST Channel](./connectors/your-own-website.mdx) A messaging channel used to build custom connectors. Includes an input channel, where user messages can be posted to Rasa, and the ability to specify a callback URL, where the bot’s response actions will be sent. @@ -177,12 +177,12 @@ Dual Intent and Entity Transformer. The default NLU architecture used by Rasa, w ## [Story](./stories.mdx) - Training data format for the dialogue model, consisting of a conversation between a user and a bot. The user's messages are represented as annotated intents and entities, and the bot’s responses are represented as a sequence of actions. - + Training data format for the dialogue model, consisting of a conversation between a user and a bot. The user's messages are represented as annotated intents and entities, and the bot’s responses are represented as a sequence of actions. + ## [TED Policy](./policies.mdx#ted-policy) - Transformer Embedding Dialogue Policy. TED is the default machine learning-based dialogue policy used by Rasa. TED complements rule-based policies by handling previously unseen situations, where no rule exists to determine the next action. - + Transformer Embedding Dialogue Policy. TED is the default machine learning-based dialogue policy used by Rasa. TED complements rule-based policies by handling previously unseen situations, where no rule exists to determine the next action. + ## [Template / Response / Utterance](./responses.mdx) A message template used to respond to a user. Can include text, buttons, images, and other attachments. @@ -200,3 +200,7 @@ Dual Intent and Entity Transformer. The default NLU architecture used by Rasa, w ## Word embedding / Word vector A vector of floating point numbers that represent the meaning of a word. Words that have similar meanings tend to have similar vectors. Word embeddings are often used as an input to machine learning algorithms. + +## Rasa Primitive + +A foundational component used for structuring conversations within Rasa, such as an intent, entity, slot, form, response, action, rule, or story. diff --git a/docs/docs/spaces.mdx b/docs/docs/spaces.mdx index 3ff5cf215841..bd9fe667ea39 100644 --- a/docs/docs/spaces.mdx +++ b/docs/docs/spaces.mdx @@ -22,14 +22,14 @@ If you have feedback (positive or negative) please share it with us on the [Rasa ::: -Spaces are a way to modularize your assistant. Oftentimes, when assistants grow, the -potential for conflicts between intents, entities, and other primitives grows alongside. +Spaces are a way to modularize your assistant. As assistants grow in scale and scope, the +potential for conflicts between intents, entities, and other [primitives](./glossary.mdx#rasa-primitive) grows as well. That is because in a regular rasa assistant all intents, entities, and actions are -available at any time, so every new capability has to play nicely with all existing -ones. Spaces introduce a basic separation between parts of the bot based on activation -and deactivation of groups of rasa primitives. Every of these groups is called a space. -Spaces are activated when certain designated intents, also called entry intents, have -been predicted. With the space activation, all the primitives in the space become +available at any time, giving the assistant more choices to distinguish between the more that gets +added. Spaces provide a basic separation between parts of the bot through the activation +and deactivation of groups of [rasa primitives](./glossary.mdx#rasa-primitive). Each of these groups is called a Space. +Spaces are activated when certain designated intents, called entry intents, are +predicted. With the activation of a Space, all the primitives for the Space become available for subsequent interactions with the user. Good ways to think about spaces are * that they allow you to specify follow-up primitives, which only become accessible after another intent has come beforehand @@ -264,4 +264,4 @@ Space B: "IB"-> "iron bank". A warning is given that one value overwrites the ot defines it a synonym. Any entity with value IB will always be mapped to that synonym no matter which space is active. -For lookup tables no adverse interactions are known. \ No newline at end of file +For lookup tables no adverse interactions are known. diff --git a/pyproject.toml b/pyproject.toml index 258b1d973c2e..ceaae40fd00e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -9,7 +9,7 @@ exclude = "((.eggs | .git | .pytest_cache | build | dist))" [tool.poetry] name = "rasa" -version = "3.5.9" +version = "3.5.10" description = "Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants" authors = [ "Rasa Technologies GmbH ",] maintainers = [ "Tom Bocklisch ",] diff --git a/rasa/version.py b/rasa/version.py index 426db8451ad0..fa3717ac3229 100644 --- a/rasa/version.py +++ b/rasa/version.py @@ -1,3 +1,3 @@ # this file will automatically be changed, # do not add anything but the version number here! -__version__ = "3.5.9" +__version__ = "3.5.10"