add_first

app.py

@@ -0,0 +1,70 @@
+import gradio as gr
+import pandas as pd
+from languageexport.crew import LanguagesExport
+import tempfile
+import os
+
+def process_excel(file, output_name):
+    if not file or not output_name.strip():
+        return "Please upload a file and provide a valid name.", None, None
+
+    try:
+        df = pd.read_excel(file.name)
+        table = [df.columns.tolist()] + df.values.tolist()
+
+        result = LanguagesExport().crew().kickoff(inputs={"data": table})
+        result_df = pd.DataFrame(data=result["data"][1:], columns=result["data"][0])
+        
+        temp_dir = tempfile.mkdtemp()
+        output_file_path = os.path.join(temp_dir, f"{output_name.strip()}.xlsx")
+        result_df.to_excel(output_file_path, index=False)
+
+        return "✅ Export completed successfully!", result_df, output_file_path
+
+    except Exception as e:
+        return f"❌ Error: {str(e)}", None, None
+
+
+def show_input_table(file):
+    if file is None:
+        return gr.update(visible=True, value=None)
+    try:
+        df = pd.read_excel(file.name)
+        return gr.update(visible=True, value=df)
+    except Exception as e:
+        return gr.update(visible=True, value=None)
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 📄 Language Export Assistant")
+    gr.Markdown("Upload an Excel file, define the export filename, and run the export process.")
+
+    with gr.Row():
+        file_input = gr.File(label="Upload Excel File", file_types=[".xlsx", ".xls"])
+        file_name = gr.Textbox(label="Output file name (without extension)", placeholder="e.g. translated_table")
+
+    run_button = gr.Button("Run Export")
+
+    status_output = gr.Textbox(label="Status", interactive=False)
+
+    # Luôn hiển thị layout, chỉ update nội dung
+    with gr.Row():
+        table_input = gr.Dataframe(label="Input Table")
+        table_output = gr.Dataframe(label="Result Table")
+    
+    download_output = gr.File(label="Download Result File", visible=False)
+
+    file_input.change(fn=show_input_table, inputs=file_input, outputs=table_input)
+
+    def on_run(file, name):
+        status, df, path = process_excel(file, name)
+        is_valid_df = df is not None and not df.empty
+        return (
+            status,
+            gr.update(value=df if is_valid_df else None),
+            gr.update(value=path if path else None, visible=path is not None),
+        )
+
+    run_button.click(on_run, inputs=[file_input, file_name], outputs=[status_output, table_output, download_output])
+
+if __name__ == "__main__":
+    demo.launch(share=True)

languageexport/config/agents.yaml

@@ -0,0 +1,19 @@
+translator_researcher:
+  role: >
+    Translation Data Specialist & Localization Engineer  
+    (Expert Level)
+  goal: >
+    Ensure the entire 2D translation table is accurately completed:
+    - Automatically generate and refine any missing English phrases from the 'String' keys.
+    - Accurately fill all remaining translation cells with fluent, natural translations in Title Case, without copying English phrases directly.
+    - Preserve the table's structure exactly (no new columns, no reordering).
+  backstory: >
+      You are a translation and localization expert with 20 years of experience working on multilingual software projects.
+      You have reviewed tens of thousands of translation entries across over 40 languages.
+      You master the principles of high-quality localization and take extra care to avoid machine-like or unnatural results.
+      Your working style is meticulous—reviewing every cell without omission, never altering or adding columns unnecessarily.
+      You  always double-check every translation
+      You never leave cells half-done.
+      You **never** assume a missing language exists.
+      Your translations feel human — thoughtful, localized, and clean.
+

languageexport/config/tasks.yaml

@@ -0,0 +1,39 @@
+research_task:
+  description: >
+    You will be given {data}, a 2D Python List[List[str|None]] structured as follows:
+      - Row 0 is the header: the first column is always 'String', and the rest are language names.
+      - Rows 1…n contain translation data for each key.
+    YOU MUST identify the list of language columns **explicitly** from the header row for translating later.
+    ONLY and must translate into languages that are actually present — do NOT assume or invent or copy (for example copy English phase to French language).
+
+    Your responsibilities:
+      1. Parse the headers to identify all **existing** language columns.
+        → DO NOT assume the existence of any column unless explicitly present.
+        → DO NOT create new columns (e.g., 'English').
+
+      2. For each row:
+        a. Derive the English phrase from the 'String' key:
+          - Remove the prefix 'STR_'
+          - Replace all underscores with spaces
+          - Convert the phrase to Title Case
+        b. Use this derived phrase as the translation base.
+        c. IMPORTANT STEP: For each language cell:
+          - If the cell is:
+              • Empty  
+              • Null  
+              • Whitespace  
+              • **OR exactly matches `english_phrase`** (**CRITICAL**: this is not a valid translation!)
+              → Then translate `english_phrase` into the TARGET LANGUAGE.
+              → The translation must:
+                • Be natural and fluent  
+                • Match Title Case  
+                • Contain **no** extra punctuation, quotes, or added words  
+          - Otherwise: leave the cell unchanged.
+  expected_output: >
+     A 2D Python `List[List[str]]` of identical shape where:
+      - All originally missing translation cells are now correctly filled
+      - Table structure is preserved exactly (no added columns, no reordering)
+      - Existing non-empty translations remain unchanged
+      - All derived English phrases are used strictly as translation bases
+      - All new translations follow capitalization and output rules strictly
+  agent: translator_researcher

languageexport/crew.py

@@ -0,0 +1,44 @@
+from crewai import Agent, Crew, Process, Task,LLM
+from crewai.project import CrewBase, agent, crew, task
+import os
+from languageexport.tools.custom_tool import SaveTranslationInput
+import pandas as pd     
+os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
+os.environ["OPENROUTER_API_KEY"] = os.getenv("OPENROUTER_API_KEY")
+name_0="openrouter/tngtech/deepseek-r1t-chimera:free"
+name_z="openrouter/meta-llama/llama-4-scout:free"
+name="openai/gpt-4.1-mini-2025-04-14"
+llm=LLM(
+    model=name_z,
+    temperature=0.0,
+)
+import yaml
+
+@CrewBase
+class LanguagesExport():
+    def __init__(self):
+        agents_config = yaml.safe_load(open(r'D:\CrewAI\crew\languageexport\src\languageexport\config\agents.yaml', encoding='utf-8'))
+        tasks_config = yaml.safe_load(open(r'D:\CrewAI\crew\languageexport\src\languageexport\config\tasks.yaml', encoding='utf-8'))
+    @agent
+    def translator_researcher(self) -> Agent:
+        return Agent(
+            config=self.agents_config['translator_researcher'],
+            llm=llm,
+            verbose=True
+        )
+
+    @task
+    def research_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['research_task'],
+            output_pydantic=SaveTranslationInput,
+        )
+
+    @crew
+    def crew(self) -> Crew:
+        return Crew(
+            agents=[self.translator_researcher()],
+            tasks=[self.research_task()],
+            process=Process.sequential,
+            verbose=True
+        )

languageexport/flow.py

@@ -0,0 +1,46 @@
+from crewai.flow.flow import Flow,listen,start
+import json
+import os
+from typing import List, Dict,Any
+from pydantic import BaseModel, Field
+from crewai.flow.flow import Flow, listen, start
+import pandas as pd
+from languageexport.crew import LanguagesExport
+class OutputFile(Flow):
+    @start()
+    def get_data(self):
+        path = input("Enter path to your Excel file (e.g., full_translations.xlsx): ").strip()
+        if not os.path.exists(path):
+            raise FileNotFoundError(f"File not found: {path}")
+        df = pd.read_excel(path)
+        print(f"Loaded {path} with shape {df.shape}")
+        table = [df.columns.tolist()] + df.values.tolist()
+        self.state['table'] = table
+        return table
+
+    @listen(get_data)
+    def ask_filename(self, table: List[List[Any]]):
+        filename = input("Enter desired output filename (with .xlsx extension): ").strip()
+        if not filename.lower().endswith('.xlsx'):
+            filename += '.xlsx'
+        self.state['filename'] = filename
+        return table
+
+    @listen(ask_filename)
+    def create_file(self, table: List[List[Any]]):
+        filename = self.state['filename']
+        result = LanguagesExport().crew().kickoff(inputs={'data': table, 'filename': filename})
+        self.state['result'] = result
+        print(f"Agent returned: {result}")
+        if os.path.exists(filename):
+            print(f"Output file created: {filename}")
+        else:
+            print(f"Expected output file not found: {filename}")
+        return filename
+
+    @listen(create_file)
+    def show_file(self, filename: str):
+        df = pd.read_excel(filename)
+        print("✅ Translated content:")
+        print(df)
+        return df

languageexport/main.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+import sys
+import warnings
+
+from datetime import datetime
+from typing import List, Dict, Any
+
+import os
+
+import json
+from pydantic import BaseModel, Field
+from languageexport.flow import OutputFile
+from languageexport.crew import LanguagesExport
+import pandas as pd
+import tkinter as Tk
+from tkinter import Tk
+
+from tkinter import filedialog
+from tkinter import messagebox
+from tkinter.filedialog import askopenfilename, asksaveasfilename
+warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
+
+def run():
+    """
+    Run the crew.
+    """
+    Tk().withdraw()
+
+    # Mở hộp thoại chọn file
+    print("Vui lòng chọn file Excel đầu vào")
+    
+    file_path = askopenfilename(
+        title="Chọn file Excel đầu vào",
+        filetypes=[("Excel files", "*.xlsx *.xls")]
+    )
+    print(f"đường dẫn:{file_path}")
+    file_name=input("Enter the file name: ")
+    file_name_save=f"{file_name}.xlsx"
+    df= pd.read_excel(file_path)
+    table = [df.columns.tolist()] + df.values.tolist()
+    print(table)
+    rs=LanguagesExport().crew().kickoff(inputs={'data':table})
+    df = pd.DataFrame(data=rs["data"][1:], columns=rs["data"][0])
+    df.to_excel(file_name_save, index=False)
+
+def train():
+    """
+    Train the crew for a given number of iterations.
+    """
+    
+    inputs = {
+        'data':'table'
+    }
+    try:
+        LanguagesExport().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)
+
+    except Exception as e:
+        raise Exception(f"An error occurred while training the crew: {e}")
+
+def replay():
+    """
+    Replay the crew execution from a specific task.
+    """
+    try:
+        LanguagesExport().crew().replay(task_id=sys.argv[1])
+
+    except Exception as e:
+        raise Exception(f"An error occurred while replaying the crew: {e}")
+
+def test():
+    """
+    Test the crew execution and returns the results.
+    """
+    inputs = {
+        "topic": "AI LLMs",
+        "current_year": str(datetime.now().year)
+    }
+    try:
+        LanguagesExport().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)
+
+    except Exception as e:
+        raise Exception(f"An error occurred while testing the crew: {e}")

languageexport/tools/custom_tool.py

@@ -0,0 +1,7 @@
+from crewai.tools import BaseTool
+from typing import Type
+from pydantic import BaseModel, Field
+from typing import List, Any,Annotated
+import pandas as pd
+class SaveTranslationInput(BaseModel):
+    data: List[List[Any]] = Field(..., description="2D list representing the full translation table. The first row is the header.",strict=True)

pyproject.toml

@@ -0,0 +1,26 @@
+[project]
+name = "languageexport"
+version = "0.1.0"
+description = "LanguageExport using crewAI"
+authors = [{ name = "Your Name", email = "you@example.com" }]
+requires-python = ">=3.10,<3.13"
+dependencies = [
+    "crewai[tools]>=0.114.0,<1.0.0",
+    "gradio>=5.25.2",
+    "pandas>=2.2.3",
+    "tk>=0.1.0",
+]
+
+[project.scripts]
+languageexport = "languageexport.main:run"
+run_crew = "languageexport.main:run"
+train = "languageexport.main:train"
+replay = "languageexport.main:replay"
+test = "languageexport.main:test"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.crewai]
+type = "crew"

requirements.txt

@@ -0,0 +1,7 @@
+crewai[tools]>=0.114.0,<1.0.0
+gradio>=5.25.2
+pandas>=2.2.3
+tk
+openpyxl
+pyyaml
+numpy