Upload 3 files

main.py

@@ -0,0 +1,38 @@
+import streamlit as st
+from models_api import get_answer, get_hugging_face_answer
+
+# Define Streamlit app
+def main():
+    st.title("Document Analysis Tool")
+
+    # File upload
+    uploaded_file = st.file_uploader("Upload a text file", type=["txt"])
+    
+    if uploaded_file:
+        file_contents = uploaded_file.read().decode("utf-8")
+        st.text_area("File Content", file_contents, height=200)
+
+        # User input question
+        question = st.text_input("Enter your question")
+
+        if st.button("Get Answer"):
+            if question:
+                # Call API functions based on user choice
+                st.write("Response from Llama3 8b:")
+                answer_llama3 = get_answer("llama3", file_contents, question)
+                # answer_llama3 = get_hugging_face_answer("meta-llama/Meta-Llama-3-8B-Instruct", file_contents, question)
+                st.write(answer_llama3)
+
+                st.write("Response from Mistral 7b:")
+                answer_mistral7b = get_answer("mistral", file_contents, question)
+                # answer_mistral7b = get_hugging_face_answer("mistralai/Mistral-7B-Instruct-v0.1", file_contents, question)
+                st.write(answer_mistral7b)
+
+                st.write("Response from Gemma 7b:")
+                # answer_gemma7b = get_answer("gemma", file_contents, question)
+                answer_gemma7b = get_hugging_face_answer("google/gemma-7b-it", file_contents, question)
+                st.write(answer_gemma7b)
+
+# Run Streamlit app
+if __name__ == "__main__":
+    main()

models_api.py

@@ -0,0 +1,57 @@
+import requests
+import json
+import os
+from dotenv import load_dotenv
+load_dotenv()
+
+def get_answer(model_name, context, question):    
+    llm_key = os.getenv("llm_key")
+    url = os.getenv("main_url")
+    # Construct the prompt for the model
+    prompt = f"You are a Question Answering Model. Can you help me answer the question: {question} from the context: {context}? Just return the answer only. The document may contain some Arabic text; please translate that to English if needed."
+
+    # Prepare payload for API request
+    payload = {
+        "model": model_name,
+        "messages": [
+            {
+                "role": "user",
+                "content": prompt
+            }
+        ],
+        "max_tokens": 300,
+        "temperature": 0.2
+    }
+    
+    headers = {
+        'Authorization': f'Bearer {llm_key}',
+        'Content-Type': 'application/json'
+    }
+    
+    # Convert payload to JSON string
+    json_payload = json.dumps(payload)
+    
+    try:
+        # Send POST request to the API
+        response = requests.post(url, headers=headers, data=json_payload)
+        
+        # Check if request was successful
+        if response.status_code == 200:            
+            response_data = response.json()                                 # Parse response JSON            
+            answer = response_data['choices'][0]['message']['content']      # Extract model's answer from response
+            return answer
+        else:
+            print(f"Request failed with status code: {response.status_code}")
+            return None
+    
+    except requests.exceptions.RequestException as e:
+        print(f"Error occurred: {e}")
+        return None
+
+from huggingface_hub import InferenceClient
+
+def get_hugging_face_answer(model_name, context, question):
+    client = InferenceClient(model_name, token=os.getenv("HF_TOKEN"))
+    prompt = f"You are a Question Answering Model. Can you help me answer the question: {question} from the context: {context}? Just return the answer only. The document may contain some Arabic text; please translate that to English if needed."
+    output = client.text_generation(prompt , max_new_tokens = 200, stream=True, temperature=0.1)
+    return output

requirements.txt

@@ -0,0 +1,48 @@
+altair==5.3.0
+attrs==23.2.0
+blinker==1.8.1
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+filelock==3.14.0
+fsspec==2024.3.1
+gitdb==4.0.11
+GitPython==3.1.43
+huggingface-hub==0.23.0
+idna==3.7
+Jinja2==3.1.4
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+numpy==1.26.4
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+protobuf==4.25.3
+pyarrow==16.0.0
+pydeck==0.9.0
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+six==1.16.0
+smmap==5.0.1
+streamlit==1.34.0
+tenacity==8.2.3
+toml==0.10.2
+toolz==0.12.1
+tornado==6.4
+tqdm==4.66.4
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+watchdog==4.0.0