writinwaters commited on
Commit
5c37eb6
·
1 Parent(s): 24ea1d7

Updated component descriptions (#2293)

Browse files

### What problem does this PR solve?


### Type of change


- [x] Documentation Update

agent/templates/DB Assistant.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "id": 6,
3
  "title": "DB Assistant",
4
- "description": "A more advanced agent that converts user queries into SQL statements, executes the queries, and assesses and returns the results. You must prepare three knowledge bases: 1: DDL for your database; 2: Examples of user queries converted to SQL statements; 3: A comprehensive description of your database, including but not limited to tables and records. And you are also required to configure the corresponding database.",
5
  "canvas_type": "chatbot",
6
  "dsl": {
7
  "answer": [],
 
1
  {
2
  "id": 6,
3
  "title": "DB Assistant",
4
+ "description": "An advanced agent that converts user queries into SQL statements, executes the queries, and assesses and returns the results. You must prepare three knowledge bases: 1: DDL for your database; 2: Examples of user queries converted to SQL statements; 3: A comprehensive description of your database, including but not limited to tables and records. You are also required to configure the corresponding database.",
5
  "canvas_type": "chatbot",
6
  "dsl": {
7
  "answer": [],
web/src/locales/en.ts CHANGED
@@ -647,16 +647,16 @@ The above is the content you need to summarize.`,
647
  run: 'Run',
648
  save: 'Save',
649
  title: 'Title:',
650
- beginDescription: 'This is where the flow begin',
651
- answerDescription: `This component is used as an interface between bot and human. It receives input of user and display the result of the computation of the bot.`,
652
- retrievalDescription: `This component is for the process of retrieving relevent information from knowledge base. So, knowledgebases should be selected. If there's nothing retrieved, the 'Empty response' will be returned.`,
653
- generateDescription: `This component is used to call LLM to generate text. Be careful about the prompt setting.`,
654
- categorizeDescription: `This component is used to categorize text. Please specify the name, description and examples of the category. Every single category leads to different downstream components.`,
655
- relevantDescription: `This component is used to judge if the output of upstream is relevent to user's latest question. 'Yes' represents that they're relevant. 'No' represents they're irrelevant.`,
656
- rewriteQuestionDescription: `This component is used to refine user's quesion. Typically, when a user's original question can't retrieve relevant information from knowledge base, this component help you change the question into a proper one which might be more consistant with the expressions in knowledge base. Only 'Retrieval' can be its downstreams.`,
657
  messageDescription:
658
- 'This component is used to send user static information. You can prepare several messages which will be chosen randomly.',
659
- keywordDescription: `This component is used to extract keywords from user's question. Top N specifies the number of keywords you need to extract.`,
660
  wikipediaDescription: `This component is used to get search result from https://www.wikipedia.org/. Typically, it performs as a supplement to knowledgebases. Top N specifies the number of search results you need to adapt.`,
661
  promptText: `Please summarize the following paragraphs. Be careful with the numbers, do not make things up. Paragraphs as following:
662
  {input}
 
647
  run: 'Run',
648
  save: 'Save',
649
  title: 'Title:',
650
+ beginDescription: 'This is where the flow begins.',
651
+ answerDescription: `A component that serves as the interface between human and bot, receiving user inputs and displaying the agent's responses.`,
652
+ retrievalDescription: `A component that retrieves information from a specified knowledge base and returns 'Empty response' if no information is found. Ensure the correct knowledge base is selected.`,
653
+ generateDescription: `A component that prompts the LLM to generate responses. Ensure the prompt is set correctly.`,
654
+ categorizeDescription: `A component that uses the LLM to classify user inputs into predefined categories. Ensure you specify the name, description, and examples for each category, along with the corresponding next component.`,
655
+ relevantDescription: `A component that uses the LLM to assess whether the upstream output is relevant to the user's latest query. Ensure you specify the next component for each judge result.`,
656
+ rewriteQuestionDescription: `A component that refines a user query if it fails to retrieve relevant information from the knowledge base. It repeats this process until the predefined looping upper limit is reached. Ensure its upstream is 'Relevant' and downstream is 'Retrieval'. `,
657
  messageDescription:
658
+ "A component that sends out a static message. If multiple messages are supplied, it randomly selects one to send. Ensure its downstream is 'Answer', the interface component.",
659
+ keywordDescription: `A component that retrieves top N search results from wikipedia.org. Ensure the TopN value is set properly before use.`,
660
  wikipediaDescription: `This component is used to get search result from https://www.wikipedia.org/. Typically, it performs as a supplement to knowledgebases. Top N specifies the number of search results you need to adapt.`,
661
  promptText: `Please summarize the following paragraphs. Be careful with the numbers, do not make things up. Paragraphs as following:
662
  {input}