modified

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Albert NIYONSENGA
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -10,5 +10,8 @@ pinned: false
 license: mit
 short_description: This chatbot uses the Llm model.
 ---
+# LLM-Files-QA
+
+Whether for research, customer support, or personal projects, this repository provides an idea for building scalable and practical solution for document Q&A using LLMs.
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,86 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Sidebar 
+with st.sidebar:
+    st.markdown("## About Fela")
+    st.markdown("This chatbot uses the Llm model to answer questions based on the content of an uploaded article. You can upload a text or markdown file and ask questions about its content.")
+    st.markdown("[View the source code](https://github.com/Al0ni/LLM-Files-QA/blob/main/app.py)")
+    st.markdown("[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/Al04ni/LLM-Files-QA?quickstart=1)")
+
+# Main interface
+st.title(" File Q&A 📝 with Fela")
+
+# Initialize variables for model and tokenizer
+model_name = "meta-llama/Llama-2-7b-chat-hf"
+tokenizer, model = None, None
+
+try:
+    # Attempt to load the tokenizer and model
+    with st.spinner("Loading model and tokenizer..."):
+        tokenizer = AutoTokenizer.from_pretrained(model_name, token=True)
+        model = AutoModelForCausalLM.from_pretrained(model_name, token=True)
+    st.success("Model and tokenizer loaded successfully!")
+except Exception as e:
+    st.error("Failed to load the model or tokenizer. Please check your configuration.")
+    st.warning(f"Error Details: {e}")
+    st.stop()  # Stop execution if model loading fails
+
+# Add tabs for suggested questions, easing kabisa
+tabs = st.tabs(["Summary", "Key Points", "Actionable Insights", "Critical Analysis", "General"])
+
+#questions suggested for each tab
+suggested_questions = {
+    "Summary": ["Can you summarize the article?", "What are the main points discussed?"],
+    "Key Points": ["What are the key takeaways?", "What facts are highlighted in the article?"],
+    "Actionable Insights": ["What actions can be taken based on this article?", "How can the information be applied?"],
+    "Critical Analysis": ["Are there any biases present?"],
+    "General": ["Can you rewrite the article?", "Who is the intended audience for this article?"]
+}
+
+# Display  questions in tabs
+selected_question = ""
+for tab_name, questions in suggested_questions.items():
+    with tabs[list(suggested_questions.keys()).index(tab_name)]:
+        st.markdown(f"### Suggested Questions: {tab_name}")
+        for question in questions:
+            if st.button(question, key=f"{tab_name}_{question}"):
+                selected_question = question
+
+# File uploader and question input
+uploaded_file = st.file_uploader("Upload an article", type=("txt", "md"))
+question = st.text_input(
+    "Ask something about the article",
+    value=selected_question,  # Populate the selected question
+    placeholder="Can you give me a short summary?",
+    disabled=not uploaded_file,
+)
+
+if uploaded_file and question:
+    article = uploaded_file.read().decode()
+    prompt = f"Here's an article:\n\n<article>\n{article}\n</article>\n\n{question}"
+
+    try:
+        # Tokenize the input
+        inputs = tokenizer(prompt, return_tensors="pt")
+
+        # Generate the response
+        with torch.no_grad():
+            with st.spinner("Generating response..."):
+                outputs = model.generate(inputs.input_ids, max_length=150)
+
+        # Decode the response
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        st.write("### Answer")
+        st.write(response)
+
+    except Exception as e:
+        st.error("An error occurred while processing your query.")
+        st.warning(f"Error Details: {e}")
+else:
+    if not uploaded_file:
+        st.info("Please upload a file to get started.")
+    elif not question:
+        st.info("Please enter a question to ask about the uploaded file.")

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+transformers
+torch