feat: add app

.gitignore

@@ -0,0 +1,176 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/
+
+# PyPI configuration file
+.pypirc
+
+images/
+vectorstore/
+trial.py
+annotations/

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -11,4 +11,133 @@ license: apache-2.0
 short_description: 🧠 Multimodal RAG that "weaves" together text and images 🪡
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🌟 LoomRAG: Multimodal Retrieval-Augmented Generation for AI-Powered Search
+
+![GitHub stars](https://img.shields.io/github/stars/NotShrirang/LoomRAG?style=social)
+![GitHub forks](https://img.shields.io/github/forks/NotShrirang/LoomRAG?style=social)
+![GitHub commits](https://img.shields.io/github/commit-activity/t/NotShrirang/LoomRAG)
+![GitHub issues](https://img.shields.io/github/issues/NotShrirang/LoomRAG)
+![GitHub pull requests](https://img.shields.io/github/issues-pr/NotShrirang/LoomRAG)
+![GitHub](https://img.shields.io/github/license/NotShrirang/LoomRAG)
+![GitHub last commit](https://img.shields.io/github/last-commit/NotShrirang/LoomRAG)
+![GitHub repo size](https://img.shields.io/github/repo-size/NotShrirang/LoomRAG)
+<a href="https://loomrag.streamlit.app/"><img src="https://img.shields.io/badge/Streamlit%20App-red?style=flat-rounded-square&logo=streamlit&labelColor=white"/></a>
+
+This project implements a Multimodal Retrieval-Augmented Generation (RAG) system, named **LoomRAG**, that leverages OpenAI's CLIP model for neural cross-modal retrieval and semantic search. The system allows users to input text queries and retrieve both text and image responses seamlessly through vector embeddings. It also supports uploading images and PDFs for enhanced interaction and intelligent retrieval capabilities through a Streamlit-based interface.
+
+Experience the project in action:
+
+[![LoomRAG Streamlit App](https://img.shields.io/badge/Streamlit%20App-red?style=for-the-badge&logo=streamlit&labelColor=white)](https://loomrag.streamlit.app/)
+
+---
+
+## 📸 Implementation Screenshots
+
+| ![Screenshot 2024-12-30 111906](https://github.com/user-attachments/assets/13c0bd0d-1569-4d9e-aae5-ea5801a69beb) | ![Screenshot 2024-12-30 114200](https://github.com/user-attachments/assets/d74e9d75-7716-4705-9564-0c6fdc26790b) |
+| ---------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
+| Screenshot 1                                                                                                     | Screenshot 2                                                                                                     |
+
+---
+
+## ✨ Features
+
+- 🔄 **Cross-Modal Retrieval**: Search text to retrieve both text and image results using deep learning
+- 🌐 **Streamlit Interface**: Provides a user-friendly web interface for interacting with the system
+- 📤 **Upload Options**: Allows users to upload images and PDFs for AI-powered processing and retrieval
+- 🧠 **Embedding-Based Search**: Uses OpenAI's CLIP model to align text and image embeddings in a shared latent space
+- 🔍 **Augmented Text Generation**: Enhances text results using LLMs for contextually rich outputs
+
+---
+
+## 🏗️ Architecture Overview
+
+1. **Data Indexing**:
+
+   - Text, images, and PDFs are preprocessed and embedded using the CLIP model
+   - Embeddings are stored in a vector database for fast and efficient retrieval
+
+2. **Query Processing**:
+
+   - Text queries are converted into embeddings for semantic search
+   - Uploaded images and PDFs are processed and embedded for comparison
+   - The system performs a nearest neighbor search in the vector database to retrieve relevant text and images
+
+3. **Response Generation**:
+   - For text results: Optionally refined or augmented using a language model
+   - For image results: Directly returned or enhanced with image captions
+   - For PDFs: Extracts text content and provides relevant sections
+
+---
+
+## 🚀 Installation
+
+1. Clone the repository:
+
+   ```bash
+   git clone https://github.com/NotShrirang/LoomRAG.git
+   cd LoomRAG
+   ```
+
+2. Create a virtual environment and install dependencies:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+---
+
+## 📖 Usage
+
+1. **Running the Streamlit Interface**:
+
+   - Start the Streamlit app:
+
+     ```bash
+     streamlit run app.py
+     ```
+
+   - Access the interface in your browser to:
+     - Submit natural language queries
+     - Upload images or PDFs to retrieve contextually relevant results
+
+2. **Example Queries**:
+   - **Text Query**: "sunset over mountains"  
+     Output: An image of a sunset over mountains along with descriptive text
+   - **PDF Upload**: Upload a PDF of a scientific paper  
+     Output: Extracted key sections or contextually relevant images
+
+---
+
+## ⚙️ Configuration
+
+- 📊 **Vector Database**: It uses FAISS for efficient similarity search
+- 🤖 **Model**: Uses OpenAI CLIP for neural embedding generation
+- ✍️ **Augmentation**: Optional LLM-based augmentation for text responses
+
+---
+
+## 🗺️ Roadmap
+
+- [ ] Fine-tuning CLIP for domain-specific datasets
+- [ ] Adding support for audio and video modalities
+- [ ] Improving the re-ranking system for better contextual relevance
+- [ ] Enhanced PDF parsing with semantic section segmentation
+
+---
+
+## 🤝 Contributing
+
+Contributions are welcome! Please open an issue or submit a pull request for any feature requests or bug fixes.
+
+---
+
+## 📄 License
+
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
+
+---
+
+## 🙏 Acknowledgments
+
+- [OpenAI CLIP](https://openai.com/research/clip)
+- [FAISS](https://github.com/facebookresearch/faiss)
+- [Hugging Face](https://huggingface.co/)

app.py

@@ -0,0 +1,43 @@
+import clip
+import faiss
+import os
+import pandas as pd
+from PIL import Image
+import streamlit as st
+from streamlit_option_menu import option_menu
+import time
+import torch
+
+from data_upload import data_upload_page
+from data_search import data_search_page
+from data_annotations import data_annotation_page
+from model_finetuning import model_finetuning_page
+from utils import load_clip_model, load_text_embedding_model
+
+os.environ['KMP_DUPLICATE_LIB_OK']='True'
+
+st.set_page_config(layout="wide", page_title="LoomRAG", page_icon="🔍")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+clip_model, preprocess = load_clip_model()
+text_embedding_model = load_text_embedding_model()
+
+sidebar = st.sidebar
+
+with st.sidebar:
+    st.title("LoomRAG")
+    page = option_menu(
+        menu_title=None,
+        options=["Data Upload", 'Data Search', "Data Annotation", "Model Fine-Tuning"], 
+        icons=['cloud-upload', 'search', 'bi-card-checklist', 'sliders'],
+        menu_icon="list", default_index=0
+    )
+
+if page == "Data Upload":
+    data_upload_page.data_upload(clip_model, preprocess, text_embedding_model)
+if page == "Data Search":
+    data_search_page.data_search(clip_model, preprocess, text_embedding_model, device)
+if page == "Data Annotation":
+    data_annotation_page.data_annotations()
+if page == "Model Fine-Tuning":
+    model_finetuning_page.model_finetuning()

data_annotations/data_annotation_page.py

@@ -0,0 +1,77 @@
+import base64
+import clip
+import io
+import json
+import os
+import pandas as pd
+from PIL import Image
+import streamlit as st
+import sys
+import torch
+import uuid
+
+from utils import get_local_files
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+
+def data_annotations():
+    @st.dialog("Add Annotations", width="large")
+    def add_annotations_dialog(selected_image):
+        if not os.path.exists("annotations/"):
+            os.makedirs("annotations/")
+        annotation_project_key = st.session_state.get('annotation_project_key', None)
+        if not annotation_project_key:
+            annotation_project_key = str(uuid.uuid4())
+            st.session_state['annotation_project_key'] = annotation_project_key
+        if not os.path.exists(f"annotations/{annotation_project_key}/"):
+            os.makedirs(f"annotations/{annotation_project_key}/")
+            with open(f"annotations/{annotation_project_key}/annotations.json", "w") as f:
+                json.dump({}, f)
+        with open(f"annotations/{annotation_project_key}/annotations.json", "r") as f:
+            annotations_dict: dict = json.load(f)
+
+        current_image_annotation = annotations_dict.get(f"images/{selected_image['file_name']}", None)
+        if not current_image_annotation:
+            current_image_annotation = ""
+
+        st.image(f"images/{selected_image['file_name']}")
+        annotation = st.text_area("Add Annotations", value=current_image_annotation, height=100, key="annotation_text_area")
+        if st.button("Add Annotations", key="add_annotations_dialog"):
+            if annotation.strip() == "" or annotation is None:
+                st.warning("Please add annotations.")
+            else:
+                annotations_dict[f"images/{selected_image['file_name']}"] = annotation
+                with open(f"annotations/{annotation_project_key}/annotations.json", "w") as f:
+                    json.dump(annotations_dict, f, indent=4)
+                st.toast("Annotations added successfully.", icon="🎉")
+                st.rerun()
+
+    st.title("Data Annotations")
+
+    files = get_local_files("images/", extensions=["jpg", "jpeg", "png"], get_details=True)
+
+    if not files:
+        st.warning("No images found in the data directory.")
+        return
+    
+    st.write(f"Total {len(files)} images found in the data directory.")
+
+    files_df = pd.DataFrame(files)
+    
+    files_df['Image'] = files_df['file_name'].apply(lambda x: f"data:image/{x.split('.')[-1]};base64,{base64.b64encode(open(f'images/{x}', 'rb').read()).decode()}")
+
+    files_df = files_df[["Image", "file_name", "file_size", "file_created"]]
+
+    if "annotation_project_key" in st.session_state:
+        annotation_project_key = st.session_state['annotation_project_key']
+        if os.path.exists(f"annotations/{annotation_project_key}/annotations.json"):
+            with open(f"annotations/{annotation_project_key}/annotations.json", "r") as f:
+                annotations_dict: dict = json.load(f)
+            files_df["Annotation"] = files_df["file_name"].apply(lambda x: annotations_dict.get(f"images/{x}", ""))
+
+    event = st.dataframe(files_df, hide_index=True, use_container_width=True, column_config={"Image" : st.column_config.ImageColumn('Image', pinned=True)}, selection_mode="single-row", on_select='rerun', key="image_table")
+
+    if len(event.selection['rows']):
+        selected_image = files[event.selection['rows'][0]]
+        add_annotations_dialog(selected_image)

data_search/data_search_page.py

@@ -0,0 +1,87 @@
+import clip
+import os
+import pandas as pd
+from PIL import Image
+import streamlit as st
+import sys
+import torch
+from vectordb import search_image_index, search_text_index
+from utils import load_image_index, load_text_index, get_local_files
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+
+def data_search(clip_model, preprocess, text_embedding_model, device):
+
+    @st.cache_resource
+    def load_finetuned_model(file_name):
+        model, preprocess = clip.load("ViT-B/32", device=device)
+        model.load_state_dict(torch.load(f"annotations/{file_name}/finetuned_model.pt", weights_only=True))
+        return model, preprocess
+
+    st.title("Data Search")
+
+    annotation_projects = get_local_files("annotations/", get_details=True)
+
+    if annotation_projects or st.session_state.get('selected_annotation_project', None) is not None:
+        annotation_projects_with_model = []
+        for annotation_project in annotation_projects:
+            if os.path.exists(f"annotations/{annotation_project['file_name']}/finetuned_model.pt"):
+                annotation_projects_with_model.append(annotation_project)
+
+        if annotation_projects_with_model or st.session_state.get('selected_annotation_project', None) is not None:
+            if st.button("Use Default Model"):
+                st.session_state.pop('selected_annotation_project', None)
+            annotation_projects_df = pd.DataFrame(annotation_projects_with_model)
+            annotation_projects_df['file_created'] = annotation_projects_df['file_created'].dt.strftime("%Y-%m-%d %H:%M:%S")
+            annotation_projects_df['display_text'] = annotation_projects_df.apply(lambda x: f"ID: {x['file_name']} | Time Created: ({x['file_created']})", axis=1)
+
+            annotation_project = st.selectbox("Select Annotation Project", options=annotation_projects_df['display_text'].tolist())
+            annotation_project = annotation_projects_df[annotation_projects_df['display_text'] == annotation_project].iloc[0]
+            if st.button("Use Selected Fine-Tuned Model") or st.session_state.get('selected_annotation_project', None) is not None:
+                with st.spinner("Loading Fine-Tuned Model..."):
+                    st.session_state['selected_annotation_project'] = annotation_project
+                    clip_model, preprocess = load_finetuned_model(annotation_project['file_name'])
+                st.info(f"Using Fine-Tuned Model from {annotation_project['file_name']}")
+            else:
+                st.info("Using Default Model")
+
+    text_input = st.text_input("Search Database")
+    if st.button("Search", disabled=text_input.strip() == ""):
+        if os.path.exists("./vectorstore/image_index.index"):
+            image_index, image_data = load_image_index()
+        if os.path.exists("./vectorstore/text_index.index"):
+            text_index, text_data = load_text_index()
+        with torch.no_grad():
+            if not os.path.exists("./vectorstore/image_data.csv"):
+                st.warning("No Image Index Found. So not searching for images.")
+                image_index = None
+            if not os.path.exists("./vectorstore/text_data.csv"):
+                st.warning("No Text Index Found. So not searching for text.")
+                text_index = None
+            if image_index is not None:
+                image_indices = search_image_index(text_input, image_index, clip_model, k=3)
+            if text_index is not None:
+                text_indices = search_text_index(text_input, text_index, text_embedding_model, k=3)
+            if not image_index and not text_index:
+                st.error("No Data Found! Please add data to the database.")
+            st.subheader("Top 3 Results")
+            cols = st.columns(3)
+            for i in range(3):
+                with cols[i]:
+                    if image_index:
+                        image_path = image_data['path'].iloc[image_indices[0][i]]
+                        image = Image.open(image_path)
+                        image = preprocess(image).unsqueeze(0).to(device)
+                        text = clip.tokenize([text_input]).to(device)
+                        image_features = clip_model.encode_image(image)
+                        text_features = clip_model.encode_text(text)
+                        cosine_similarity = torch.cosine_similarity(image_features, text_features)
+                        st.write(f"Similarity: {cosine_similarity.item() * 100:.2f}%")
+                        st.image(image_path)
+            cols = st.columns(3)
+            for i in range(3):
+                with cols[i]:
+                    if text_index:
+                        text_content = text_data['content'].iloc[text_indices[0][i]]
+                        st.write(text_content)

data_upload/data_upload_page.py

@@ -0,0 +1,43 @@
+import os
+import streamlit as st
+import sys
+from vectordb import add_image_to_index, add_pdf_to_index
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+
+def data_upload(clip_model, preprocess, text_embedding_model):
+    st.title("Data Upload")
+    upload_choice = st.selectbox(options=["Upload Image", "Upload PDF"], label="Select Upload Type")
+    if upload_choice == "Upload Image":
+        st.subheader("Add Image to Database")
+        images = st.file_uploader("Upload Image", type=["jpg", "jpeg", "png"], accept_multiple_files=True)
+        if images:
+            cols = st.columns(5, vertical_alignment="center")
+            for count, image in enumerate(images[:4]):
+                with cols[count]:
+                    st.image(image)
+            with cols[4]:
+                st.info(f"and more {len(images) - 5} images...")
+            st.info(f"Total {len(images)} files selected.")
+            if st.button("Add Images"):
+                progress_bar = st.progress(0)
+                for image in images:
+                    add_image_to_index(image, clip_model, preprocess)
+                    progress_bar.progress((images.index(image) + 1) / len(images), f"{images.index(image) + 1}/{len(images)}")
+                st.success("Images Added to Database")
+    else:
+        st.subheader("Add PDF to Database")
+        st.warning("Please note that the images in the PDF will also be extracted and added to the database.")
+        pdfs = st.file_uploader("Upload PDF", type=["pdf"], accept_multiple_files=True)
+        if pdfs:
+            st.info(f"Total {len(pdfs)} files selected.")
+            if st.button("Add PDF"):
+                for pdf in pdfs:
+                    add_pdf_to_index(
+                        pdf=pdf,
+                        clip_model=clip_model,
+                        preprocess=preprocess,
+                        text_embedding_model=text_embedding_model,
+                    )
+                st.success("PDF Added to Database")

model_finetuning/components/model_training_component.py

@@ -0,0 +1,168 @@
+import clip
+import clip.model
+from datasets import Dataset
+import json
+import numpy as np
+import pandas as pd
+from PIL import Image
+from sklearn.model_selection import train_test_split
+import streamlit as st
+import time
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader
+import tqdm
+import os
+
+
+def model_training():
+    dataset_path = st.session_state.get("selected_dataset", None)
+    if not dataset_path:
+        st.error("Please select a dataset to proceed.")
+        return
+    
+    if not os.path.exists(f"annotations/{dataset_path}/annotations.json"):
+        st.error("No annotations found for the selected dataset.")
+        return
+    
+    with open(f"annotations/{dataset_path}/annotations.json", "r") as f:
+        annotations_dict = json.load(f)
+
+    annotations_df = pd.DataFrame(annotations_dict.items(), columns=['image_path', 'annotation'])
+    annotations_df.columns = ['file_name', 'text']
+    st.subheader("Data Preview")
+    st.dataframe(annotations_df.head(), use_container_width=True)
+
+    test_size = st.selectbox("Select Test Size", options=[0.1, 0.2, 0.3, 0.4, 0.5], index=1)
+    train_df, val_df = train_test_split(annotations_df, test_size=test_size, random_state=42)
+    st.write(f"Train Size: {len(train_df)} | Validation Size: {len(val_df)}")
+    col1, col2 = st.columns(2)
+    with col1:
+        optimizer = st.selectbox("Select Optimizer", options=optim.__all__, index=3)
+        optimizer = getattr(optim, optimizer)
+    with col2:
+        batch_size_options = [2, 4, 8, 16, 32, 64, 128]
+        ideal_batch_size = int(np.sqrt(len(train_df)))
+        if ideal_batch_size in batch_size_options:
+            ideal_batch_size_index = batch_size_options.index(ideal_batch_size)
+        else:
+            for batch_size in batch_size_options:
+                if batch_size > ideal_batch_size:
+                    ideal_batch_size_index = batch_size_options.index(batch_size) - 1
+                    break
+        batch_size = st.selectbox("Select Batch Size", options=[2, 4, 8, 16, 32, 64, 128], index=ideal_batch_size_index)
+    
+    col1, col2 = st.columns(2)
+    with col1:
+        weight_decay = st.number_input("Weight Decay", value=0.3, format="%.5f")
+    with col2:
+        learning_rate = st.number_input("Learning Rate", value=1e-3, format="%.5f")
+
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+
+    if st.button("Train", key="train_button", use_container_width=True, type="primary"):
+        def convert_models_to_fp32(model):
+            for p in model.parameters():
+                p.data = p.data.float()
+                p.grad.data = p.grad.data.float()
+
+        device = "cuda:0" if torch.cuda.is_available() else "cpu"
+        with st.spinner("Loading Model..."):
+            model, preprocess = clip.load("ViT-B/32", device=device, jit=False)
+            clip.model.convert_weights(model)
+
+        loss_img = nn.CrossEntropyLoss()
+        loss_txt = nn.CrossEntropyLoss()
+        optimizer = optimizer(model.parameters(), lr=learning_rate, betas=(0.9, 0.98), eps=1e-6, weight_decay=weight_decay)
+
+        def collate_fn(batch):
+            images = []
+            texts = []
+            for entry in batch:
+                img = entry['file_name']
+                text = entry['text']
+                images.append(img)
+                texts.append(text)
+            images = [preprocess(Image.open(img_path)) for img_path in images]
+            images = torch.stack(images)
+            return images, list(texts)
+        
+        train_df['file_name'] = train_df['file_name'].str.strip()
+        val_df['file_name'] = val_df['file_name'].str.strip()
+
+        dataset = Dataset.from_pandas(train_df)
+        dataloader = DataLoader(
+            dataset,
+            batch_size=batch_size,
+            shuffle=True,
+            collate_fn=collate_fn
+        )
+
+        val_dataset = Dataset.from_pandas(val_df)
+        val_dataloader = DataLoader(
+            val_dataset,
+            batch_size=batch_size,
+            shuffle=False,
+            collate_fn=collate_fn
+        )
+
+        def calculate_val_loss(model):
+            model.eval()
+            total_loss = 0
+            with torch.no_grad():
+                for batch_idx, (images, texts) in enumerate(val_dataloader):
+                    texts = clip.tokenize(texts).to(device)
+
+                    images = images.to(device)
+                    texts = texts.to(device)
+
+                    logits_per_image, logits_per_text = model(images, texts)
+
+                    ground_truth = torch.arange(len(images)).to(device)
+                    image_loss = loss_img(logits_per_image, ground_truth)
+                    text_loss = loss_txt(logits_per_text, ground_truth)
+
+                    total_loss += (image_loss + text_loss) / 2
+
+            model.train()
+            return total_loss / len(val_dataloader)
+
+        step = 0
+        progress_bar = st.progress(0, text=f"Model Training in progress... \nStep: {step}/{len(dataloader)} | {0 / len(dataloader)}% Completed | Loss: 0.0")
+        for batch_idx, (images, texts) in enumerate(dataloader):
+            optimizer.zero_grad()
+
+            texts = clip.tokenize(texts).to(device)
+
+            images = images.to(device)
+            texts = texts.to(device)
+
+            logits_per_image, logits_per_text = model(images, texts)
+
+            ground_truth = torch.arange(len(images)).to(device)
+            image_loss = loss_img(logits_per_image, ground_truth)
+            text_loss = loss_txt(logits_per_text, ground_truth)
+            total_loss = (image_loss + text_loss) / 2
+            total_loss.backward()
+
+            if step % 20 == 0:
+                print("\nStep : ", step)
+                print("Total Loss : ", total_loss.item())
+                val_loss = calculate_val_loss(model)
+                print("\nValidation Loss : ", val_loss.item())
+                print("\n")
+
+            convert_models_to_fp32(model)
+            optimizer.step()
+            clip.model.convert_weights(model)
+            step += 1
+            progress_bar.progress((batch_idx + 1) / len(dataloader), f"Model Training in progress... \nStep: {step}/{len(dataloader)} | {round((batch_idx + 1) / len(dataloader) * 100)}% Completed | Loss: {val_loss.item():.4f}")
+
+        st.toast("Training Completed!", icon="🎉")
+
+        with st.spinner("Saving Model..."):
+            finetuned_model = model.eval()
+            torch.save(finetuned_model.state_dict(), f"annotations/{dataset_path}/finetuned_model.pt")
+
+        st.success("Model Saved Successfully!")

model_finetuning/components/selection_component.py

@@ -0,0 +1,38 @@
+import clip
+import json
+import pandas as pd
+import streamlit as st
+import torch
+import time
+
+from utils import get_local_files
+
+def preference_selection():
+    annotation_projects = get_local_files("annotations/", get_details=True)
+    if not annotation_projects:
+        st.warning("No annotated data found.")
+        return
+
+    annotation_projects_df = pd.DataFrame(annotation_projects)
+    annotation_projects_df['file_created'] = annotation_projects_df['file_created'].dt.strftime("%Y-%m-%d %H:%M:%S")
+    annotation_projects_df['display_text'] = annotation_projects_df.apply(lambda x: f"ID: {x['file_name']} | Time Created: ({x['file_created']})", axis=1)
+
+    annotation_project = st.selectbox("Select Annotation Project", options=annotation_projects_df['display_text'].tolist())
+    annotation_project = annotation_projects_df[annotation_projects_df['display_text'] == annotation_project].iloc[0]
+    with open(f"annotations/{annotation_project['file_name']}/annotations.json", "r") as f:
+        annotations_dict: dict = json.load(f)
+
+    annotations_df = pd.DataFrame(annotations_dict.items(), columns=['image_path', 'annotation'])
+    annotations_df['image_path'] = annotations_df['image_path'].apply(lambda x: x.split('/')[-1])
+    cols = st.columns(5)
+    for i, row in annotations_df.head(4).iterrows():
+        with cols[i]:
+            st.image(f"images/{row['image_path']}", caption=row['annotation'])
+    if len(annotations_df) > 4:
+        with cols[4]:
+            st.info(f"and more {len(annotations_df) - 4} images...")
+
+    save_preference = st.button("Save Preferences")
+    if save_preference:
+        st.session_state['selected_dataset'] = annotation_project['file_name']
+        st.success("Preferences Saved Successfully.")

model_finetuning/model_finetuning_page.py

@@ -0,0 +1,47 @@
+import base64
+import clip
+import io
+import json
+import os
+import pandas as pd
+from PIL import Image
+import streamlit as st
+import sys
+import torch
+import uuid
+
+from utils import get_local_files
+from model_finetuning.components import selection_component, model_training_component
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+
+def model_finetuning():
+    page = st.session_state.get("model_finetuning_page", 0)
+
+    pages = {
+        0: "Preference Selection",
+        1: "Model Training",
+        2: "Model Evaluation"
+    }
+    st.title(pages[page])
+    
+    if not torch.cuda.is_available():
+        st.warning("No GPUs detected. Model training should be done on a GPU machine or on remote instance.")
+
+    if page == 0:
+        selection_component.preference_selection()
+    elif page == 1:
+        model_training_component.model_training()
+    elif page == 2:
+        st.write("Model Evaluation")
+
+    col1, col2 = st.columns(2, gap="large")
+    if col1.button("⬅️ Back", disabled=page == 0, use_container_width=True):
+        st.session_state["model_finetuning_page"] = page - 1
+        st.rerun()
+    if col2.button("Next ➡️", disabled=page == 2, use_container_width=True):
+        st.session_state["model_finetuning_page"] = page + 1
+        st.rerun()
+
+    

requirements.txt

@@ -0,0 +1,115 @@
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.11
+aiosignal==1.3.2
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.7.0
+async-timeout==4.0.3
+attrs==24.3.0
+blinker==1.9.0
+cachetools==5.5.0
+certifi==2024.12.14
+charset-normalizer==3.4.1
+click==8.1.8
+clip @ git+https://github.com/openai/CLIP.git@dcba3cb2e2827b402d2701e7e1c7d9fed8a20ef1
+colorama==0.4.6
+contourpy==1.3.1
+cycler==0.12.1
+dataclasses-json==0.6.7
+datasets==3.2.0
+dill==0.3.8
+exceptiongroup==1.2.2
+faiss-cpu==1.8.0
+filelock==3.16.1
+fonttools==4.55.3
+frozenlist==1.5.0
+fsspec==2024.9.0
+ftfy==6.3.1
+gitdb==4.0.11
+GitPython==3.1.43
+greenlet==3.1.1
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.27.0
+idna==3.10
+Jinja2==3.1.5
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+kiwisolver==1.4.8
+langchain==0.3.13
+langchain-community==0.3.13
+langchain-core==0.3.28
+langchain-experimental==0.3.4
+langchain-text-splitters==0.3.4
+langsmith==0.1.147
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.23.2
+matplotlib==3.10.0
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.1.0
+multiprocess==0.70.16
+mypy-extensions==1.0.0
+narwhals==1.19.1
+networkx==3.4.2
+numpy==1.26.4
+open_clip_torch==2.29.0
+orjson==3.10.12
+packaging==24.2
+pandas==2.2.3
+pillow==11.0.0
+propcache==0.2.1
+protobuf==5.29.2
+pyarrow==18.1.0
+pydantic==2.10.4
+pydantic-settings==2.7.0
+pydantic_core==2.27.2
+pydeck==0.9.1
+Pygments==2.18.0
+pyparsing==3.2.0
+PyPDF2==3.0.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.2
+PyYAML==6.0.2
+referencing==0.35.1
+regex==2024.11.6
+requests==2.32.3
+requests-toolbelt==1.0.0
+rich==13.9.4
+rpds-py==0.22.3
+safetensors==0.4.5
+scikit-learn==1.6.0
+scipy==1.14.1
+sentence-transformers==3.3.1
+six==1.17.0
+smmap==5.0.1
+sniffio==1.3.1
+SQLAlchemy==2.0.36
+streamlit==1.41.1
+streamlit-option-menu==0.4.0
+sympy==1.13.1
+tenacity==8.5.0
+threadpoolctl==3.5.0
+timm==1.0.12
+tokenizers==0.21.0
+toml==0.10.2
+torch==2.5.1
+torchvision==0.20.1
+tornado==6.4.2
+tqdm==4.67.1
+transformers==4.47.1
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.3.0
+watchdog==6.0.0
+wcwidth==0.2.13
+xxhash==3.5.0
+yarl==1.18.3

utils.py

@@ -0,0 +1,60 @@
+import clip
+from datetime import datetime
+import faiss
+import pandas as pd
+import os
+from sentence_transformers import SentenceTransformer
+import streamlit as st
+import torch
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+@st.cache_resource
+def load_clip_model():
+    model, preprocess = clip.load("ViT-B/32", device=device)
+    return model, preprocess
+
+@st.cache_resource
+def load_text_embedding_model():
+    model = SentenceTransformer("all-MiniLM-L6-v2")
+    return model
+
+def load_image_index():
+    index = faiss.read_index('./vectorstore/image_index.index')
+    data = pd.read_csv("./vectorstore/image_data.csv")
+    return index, data
+
+def load_text_index():
+    index = faiss.read_index('./vectorstore/text_index.index')
+    data = pd.read_csv("./vectorstore/text_data.csv")
+    return index, data
+
+def cosine_similarity(a, b):
+    return torch.cosine_similarity(a, b)
+
+
+def get_local_files(directory: str, extensions: list = None, get_details: bool = False):
+    files = os.listdir(directory)
+    if not extensions:
+        if get_details:
+            return [{
+                "file_name": file,
+                "file_size": os.path.getsize(os.path.join(directory, file)),
+                "file_created": datetime.fromtimestamp(os.path.getctime(os.path.join(directory, file)))
+            } for file in files]
+        else:
+            return files
+    else:
+        if get_details:
+            filtered_files = []
+            for file in files:
+                file_extension = file.split(".")[-1]
+                if file_extension in extensions:
+                    filtered_files.append({
+                        "file_name": file,
+                        "file_size": os.path.getsize(os.path.join(directory, file)),
+                        "file_created": datetime.fromtimestamp(os.path.getctime(os.path.join(directory, file)))
+                    })
+            return filtered_files
+        else:
+            return [file for file in files if file.endswith(extensions(extensions))]

vectordb.py

@@ -0,0 +1,128 @@
+import clip
+import clip.model
+import faiss
+import io
+from langchain_text_splitters import CharacterTextSplitter
+import os
+import pandas as pd
+from PyPDF2 import PdfReader
+from PIL import Image
+from sentence_transformers import SentenceTransformer
+import streamlit as st
+import torch
+import time
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+os.makedirs("./vectorstore", exist_ok=True)
+
+def update_vectordb(index_path: str, embedding: torch.Tensor, image_path: str = None, text_content: str = None):
+    if not image_path and not text_content:
+        raise ValueError("Either image_path or text_content must be provided.")
+    if not os.path.exists(f"./vectorstore/{index_path}"):
+        if image_path:
+            index = faiss.IndexFlatL2(512)
+        else:
+            index = faiss.IndexFlatL2(384)
+    else:
+        index = faiss.read_index(f"./vectorstore/{index_path}")
+    try:
+        index.add(embedding.cpu().numpy())
+    except:
+        if len(embedding.shape) == 1:
+            embedding = torch.Tensor([embedding])
+        index.add(embedding)
+    faiss.write_index(index, f'./vectorstore/{index_path}')
+    if image_path:
+        if not os.path.exists("./vectorstore/image_data.csv"):
+            df = pd.DataFrame([{"path": image_path, "index": 0}]).reset_index(drop=True)
+            df.to_csv("./vectorstore/image_data.csv", index=False)
+        else:
+            df = pd.read_csv("./vectorstore/image_data.csv").reset_index(drop=True)
+            new_entry_df = pd.DataFrame({"path": image_path, "index": len(df)}, index=[0])
+            df = pd.concat([df, new_entry_df], ignore_index=True)
+            df.to_csv("./vectorstore/image_data.csv", index=False)
+    elif text_content:
+        if not os.path.exists("./vectorstore/text_data.csv"):
+            df = pd.DataFrame([{"content": text_content, "index": 0}]).reset_index(drop=True)
+            df.to_csv("./vectorstore/text_data.csv", index=False)
+        else:
+            df = pd.read_csv("./vectorstore/text_data.csv").reset_index(drop=True)
+            new_entry_df = pd.DataFrame({"content": text_content, "index": len(df)}, index=[0])
+            df = pd.concat([df, new_entry_df], ignore_index=True)
+            df.to_csv("./vectorstore/text_data.csv", index=False)
+    else:
+        raise ValueError("Either image_path or text_content must be provided.")
+    return index
+
+
+def add_image_to_index(image, model: clip.model.CLIP, preprocess):
+    image_name = image.name
+    image_name = image_name.replace(" ", "_")
+    os.makedirs("./images", exist_ok=True)
+    os.makedirs("./vectorstore", exist_ok=True)
+    with open(f"./images/{image_name}", "wb") as f:
+        try:
+            f.write(image.read())
+        except:
+            image = io.BytesIO(image.data)
+            f.write(image.read())
+    image = Image.open(f"./images/{image_name}")
+    with torch.no_grad():
+        image = preprocess(image).unsqueeze(0).to(device)
+        image_features = model.encode_image(image)
+        index = update_vectordb(index_path="image_index.index", embedding=image_features, image_path=f"./images/{image_name}")
+        return index
+
+
+def add_pdf_to_index(pdf, clip_model: clip.model.CLIP, preprocess, text_embedding_model: SentenceTransformer):
+    if not os.path.exists("./vectorstore/"):
+        os.makedirs("./vectorstore")
+    pdf_name = pdf.name
+    pdf_name = pdf_name.replace(" ", "_")
+    pdf_reader = PdfReader(pdf)
+    pdf_pages_data = []
+    pdf_texts = []
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len,
+        is_separator_regex=False,
+    )
+    progress_bar = st.progress(0)
+    for page_num, page in enumerate(pdf_reader.pages):
+        try:
+            page_images = page.images
+        except:
+            page_images = []
+            st.error("Some images in the PDF are not readable. Please try another PDF.")
+        for image in page_images:
+            image.name = f"{time.time()}.png"
+            add_image_to_index(image, clip_model, preprocess)
+            pdf_pages_data.append({f"page_number": page_num, "content": image, "type": "image"})
+
+        page_text = page.extract_text()
+        pdf_texts.append(page_text)
+        if page_text != "" or page_text.strip() != "":
+            chunks = text_splitter.split_text(page_text)
+            text_embeddings: torch.Tensor = text_embedding_model.encode(chunks)
+            for i, chunk in enumerate(chunks):
+                update_vectordb(index_path="text_index.index", embedding=text_embeddings[i], text_content=chunk)
+                pdf_pages_data.append({f"page_number": page_num, "content": chunk, "type": "text"})
+        percent_complete = ((page_num + 1) / len(pdf_reader.pages))
+        progress_bar.progress(percent_complete, f"Processing Page {page_num + 1}/{len(pdf_reader.pages)}")
+    return pdf_pages_data
+
+
+def search_image_index(text_input: str, index: faiss.IndexFlatL2, clip_model: clip.model.CLIP, k: int = 3):
+    with torch.no_grad():
+        text = clip.tokenize([text_input]).to(device)
+        text_features = clip_model.encode_text(text)
+        distances, indices = index.search(text_features.cpu().numpy(), k)
+        return indices
+
+def search_text_index(text_input: str, index: faiss.IndexFlatL2, text_embedding_model: SentenceTransformer, k: int = 3):
+    text_embeddings = text_embedding_model.encode([text_input])
+    distances, indices = index.search(text_embeddings, k)
+    return indices