Update README.md

README.md

@@ -80,7 +80,7 @@ PARAMETER stop "<s>"
 PARAMETER stop "</s>"
 ```
 
-## 💻 Ollama Python Summarizing Test Code
+## 💻 Ollama Python Summarizing Normal Test Code
 
 install all of these libraries
 ```
@@ -187,6 +187,182 @@ python pose_test.py url
 
 You can find both test results below on the section : Test Result
 
+## 💻 Ollama Python Summarizing Test Code for the target lang response
+
+install all of these libraries
+```
+pip install requests beautifulsoup4 PyPDF2 tqdm googletrans==4.0.0-rc1 langchain-community langchain
+```
+
+pose_lang.py
+```
+import sys
+import os
+import requests
+from bs4 import BeautifulSoup
+import PyPDF2
+from tqdm import tqdm
+from langchain_community.chat_models import ChatOllama
+from langchain.schema import AIMessage, HumanMessage, SystemMessage
+from googletrans import Translator
+import logging
+
+# Setup logging
+logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
+
+def clean_output(text):
+    text = text.replace("</s>", "").strip()
+    return text
+
+def translate_text(text, src_lang, dest_lang):
+    """Translates text from source language to destination language using Google Translate."""
+    if src_lang == dest_lang:
+        return text
+    translator = Translator()
+    try:
+        translation = translator.translate(text, src=src_lang, dest=dest_lang)
+        return translation.text
+    except Exception as e:
+        logging.error(f"Translation failed: {e}")
+        return text
+
+def detect_language(text):
+    """Detects the language of the given text."""
+    translator = Translator()
+    try:
+        detected = translator.detect(text)
+        return detected.lang
+    except Exception as e:
+        logging.error(f"Language detection failed: {e}")
+        return None
+
+def invoke_model(text, target_lang):
+    """Invokes the chat model and processes the response with language-specific instructions."""
+    llm = ChatOllama(model="pose:latest")
+    try:
+        # Define messages based on target language
+        if target_lang == 'ko':
+            messages = [
+                SystemMessage(content='문서의 핵심 요약을 상세하게 제공해 주실 전문가로서, 다음 문서를 요약해 주세요.'),
+                HumanMessage(content=f'다음 텍스트에 대한 전문적 요약을 제공해 주세요. 요약은 {target_lang}어의 언어적 뉘앙스에 맞게 최고 수준의 명확성과 세부 사항을 준수해야 합니다:\n\nTEXT: {text}')
+            ]
+        else:  # default to English if not Korean
+            messages = [
+                SystemMessage(content='As an adept summarizer, your expertise is required to condense the following document into its essential points in detail.'),
+                HumanMessage(content=f'Kindly provide an expert summary of the text below, adhering to the highest standards of clarity and detail. Ensure the response is tailored to the linguistic nuances of {target_lang}:\n\nTEXT: {text}')
+            ]
+
+        response = llm.invoke(messages)
+        if isinstance(response, AIMessage):
+            cleaned_content = clean_output(response.content)
+            content_lang = detect_language(cleaned_content)
+            if content_lang != target_lang:
+                return translate_text(cleaned_content, content_lang, target_lang)
+            return cleaned_content
+        else:
+            raise ValueError("Model did not return an AIMessage")
+    except Exception as e:
+        logging.error(f"Error during model invocation: {e}")
+        return "Model invocation failed."
+
+def fetch_text_from_url(url):
+    """Fetches and extracts text content from a given URL."""
+    try:
+        response = requests.get(url)
+        soup = BeautifulSoup(response.content, 'html.parser')
+        content = soup.select_one('#mw-content-text, #bodyContent, .content')
+        if not content:
+            logging.error("No content found in the expected sections.")
+            return None
+        text_content = ' '.join(p.get_text() for p in content.find_all(['p', 'li'], string=True))
+        return text_content
+    except Exception as e:
+        logging.error(f"Error fetching URL content: {e}")
+        return None
+
+def read_text_file(file_path):
+    """Reads text from a text file."""
+    try:
+        with open(file_path, "r", encoding="utf-8") as file:
+            text_content = file.read()
+        return text_content
+    except Exception as e:
+        logging.error(f"Error reading text file: {e}")
+        return None
+
+def read_pdf(file_path):
+    """Reads text from a PDF file."""
+    try:
+        with open(file_path, "rb") as file:
+            reader = PyPDF2.PdfReader(file)
+            text_content = ' '.join(page.extract_text() for page in reader.pages if page.extract_text())
+        return text_content
+    except Exception as e:
+        logging.error(f"Error reading PDF file: {e}")
+        return None
+
+def summarize_content(source, language):
+    """Processes input source (URL, file, text) and outputs a summary in the specified language."""
+    print("Processing input...")
+    text_content = None
+    if source.startswith(('http://', 'https://')):
+        print("Fetching content from URL...")
+        text_content = fetch_text_from_url(source)
+    elif os.path.isfile(source):
+        _, file_extension = os.path.splitext(source)
+        if file_extension.lower() == '.pdf':
+            print("Reading PDF...")
+            text_content = read_pdf(source)
+        elif file_extension.lower() in ['.txt', '.text']:
+            print("Reading text file...")
+            text_content = read_text_file(source)
+        else:
+            print("Unsupported file type")
+            return
+    else:
+        print("Unsupported file type")
+        return
+
+    if text_content:
+        print("Summarizing content...")
+        summary = invoke_model(text_content, language)
+        print("\n--- Summary of the document ---\n")
+        print(summary)
+    else:
+        print("No text found or unable to extract text from source.")
+
+if __name__ == '__main__':
+    if len(sys.argv) < 3:
+        print("Usage: python script.py <file_path_or_url_or_text> <language>")
+        print("Language should be 'ko' for Korean or 'en' for English.")
+    else:
+        source = sys.argv[1]
+        language = sys.argv[2]
+        summarize_content(source, language)
+
+
+```
+
+run txt file (assume txt is a.txt)
+```
+Korean response : python pose_lang a.txt ko
+English response : python pose_lang a.txt en
+```
+
+run pdf file (assume pdf is a.pdf)
+```
+Korean response : python pose_lang a.pdf ko
+English response : python pose_lang a.pdf en
+```
+
+run url (assume url is wikepedia)
+```
+Korean response : python pose_lang url ko
+English response : python pose_lang url en
+```
+
+You can find both test results below on the section : Test Result for target lang response
+
 ### 🗞️ Configuration
 The YAML configuration for this model: