New Feature: Language Selection #142
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ill-yes
suggested changes
Sep 7, 2023
notvicent3
reviewed
Oct 6, 2023
| @@ -1,89 +1,84 @@ | |||
| def generate_agent_role_prompt(agent): | |||
| def generate_agent_role_prompt(agent, language): | |||
| Returns: str: The agent role prompt. | ||
| Args: | ||
| agent (str): The type of the agent. | ||
| language (str): The language in which the answers should be provided. |
| "Business Analyst": "You are an experienced AI business analyst assistant. Your main objective is to produce comprehensive, insightful, impartial, and systematically structured business reports based on provided business data, market trends, and strategic analysis.", | ||
| "Computer Security Analyst Agent": "You are an AI specializing in computer security analysis. Your principal duty is to generate comprehensive, meticulously detailed, impartial, and systematically structured reports on computer security topics. This includes Exploits, Techniques, Threat Actors, and Advanced Persistent Threat (APT) Groups. All produced reports should adhere to the highest standards of scholarly work and provide in-depth insights into the complexities of computer security.", | ||
| "Default Agent": "You are an AI critical thinker research assistant. Your sole purpose is to write well written, critically acclaimed, objective and structured reports on given text." | ||
| "Finance Agent": f"You are a seasoned finance analyst AI assistant. Your primary goal is to compose comprehensive, astute, impartial, and methodically arranged financial reports based on provided data and trends. All answers must be in {language}.", |
There was a problem hiding this comment.
Habría que adaptarlo (si es que ha cambiado a los prompts iniciales) pero Touché.
| } | ||
|
|
||
| return prompts.get(agent, "No such agent") | ||
| return prompts.get(agent, f"No such agent. All answers must be in {language}.") |
|
|
||
|
|
||
| def generate_report_prompt(question, research_summary): | ||
|
|
||
| def generate_report_prompt(question, research_summary,language): |
There was a problem hiding this comment.
Touché. No sé realmente si la falta del espacio de research_summary, language):
Cambiaría más allá de estética.
| @@ -29,11 +29,13 @@ const GPTResearcher = (() => { | |||
| const task = document.querySelector('input[name="task"]').value; | |||
| const report_type = document.querySelector('select[name="report_type"]').value; | |||
| const agent = document.querySelector('input[name="agent"]:checked').value; | |||
|
|
|||
| const language = document.getElementById("language").value; // get language from dropdown | |||
| const requestData = { | ||
| task: task, | ||
| report_type: report_type, | ||
| agent: agent, | ||
| language: language // add language to request data |
| @@ -13,6 +13,8 @@ class ResearchRequest(BaseModel): | |||
| task: str | |||
| report_type: str | |||
| agent: str | |||
| language: str # New fiedl for language | |||
| @@ -47,6 +49,7 @@ async def websocket_endpoint(websocket: WebSocket): | |||
| task = json_data.get("task") | |||
| report_type = json_data.get("report_type") | |||
| agent = json_data.get("agent") | |||
| language = json_data.get("language") # New field for language | |||
| @@ -57,7 +60,7 @@ async def websocket_endpoint(websocket: WebSocket): | |||
|
|
|||
| await websocket.send_json({"type": "logs", "output": f"Initiated an Agent: {agent}"}) | |||
| if task and report_type and agent: | |||
| await manager.start_streaming(task, report_type, agent, agent_role_prompt, websocket) | |||
| await manager.start_streaming(task, report_type, agent, agent_role_prompt, language, websocket) # New field for language | |||
|
Languages are by default when using most LLMs so selecting the lang is redundant. |
@assafelovic The selection of output language is still in demand. Is there any way to specify the output language? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Greetings,
I've developed an enhanced feature for multi-language support:
Language Selection: This feature provides the capability to select from up to 7 different languages.
Language Selection Interface
Optimized Queries: I've implemented a total of 8 queries - 4 in English and 4 in the user-selected language to enhance search results.
Localized Reports: The system now generates reports in the user-selected language.
Report Interface
I believe this feature will greatly benefit the project by offering more versatility to users. I'm eager to contribute this to the main repository and am open to any suggestions or modifications you might have.
Thank you for considering my contribution.
Best regards,
Jose Luis Cases