Upload 14 files

.env

@@ -0,0 +1,4 @@
+GROQ_API_KEY=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
+DENSE_RETRIEVER_MODEL_NAME = all-MiniLM-L6-v2
+CROSS_ENCODER_MODEL_NAME = cross-encoder/ms-marco-MiniLM-L-12-v2
+LLM_CORE_MODEL_NAME = groq/llama3-8b-8192

.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/

.python-version

@@ -0,0 +1 @@
+3.10.2

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.

RAG_project_plan.txt

@@ -0,0 +1,11 @@
+RAG project planning:
+1. Data source: book(full english version of Count of Monte Cristo).
+2. Chunking done by size.
+3. Retriver bm25 + bi-encoder.
+4. Reranker(sentence bert).
+5. LiteLLM library (llama3-8b-8192 model).
+6. Metadata filtering wasn't used.
+7. Citation: user will be provided with the text citation along with Chapter this text belongs to.
+8. Vector database wasn't used.
+9. Web UI done with gradio
+

README.md

@@ -1,12 +1 @@
----
-title: RAGSystem
-emoji: 🐠
-colorFrom: indigo
-colorTo: green
-sdk: docker
-pinned: false
-license: apache-2.0
-short_description: RAG system based on the book 'The Count of Monte Cristo'
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Neural_Networks_RAG

chatbot/bot.py

@@ -0,0 +1,69 @@
+from chatbot.retriever import HybridRetrieverReranker
+from litellm import completion
+import os
+import ast
+
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+DENSE_RETRIEVER_MODEL_NAME = "all-MiniLM-L6-v2"
+CROSS_ENCODER_MODEL_NAME = "cross-encoder/ms-marco-MiniLM-L-12-v2"
+LLM_CORE_MODEL_NAME = "groq/llama3-8b-8192"
+
+
+class QuestionAnsweringBot:
+
+    def __init__(self, docs, enable_bm25=True, enable_dense=True, enable_rerank=True, top_k_bm25=60, top_n_dense=30, top_n_rerank=2) -> None:
+        self.retriever = HybridRetrieverReranker(docs)
+        self.enable_bm25 = enable_bm25
+        self.enable_dense = enable_dense
+        self.enable_rerank = enable_rerank
+        self.top_k_bm25=top_k_bm25
+        self.top_n_dense=top_n_dense
+        self.top_n_rerank=top_n_rerank
+
+    def __get_answer__(self, question: str) -> str:
+        PROMPT = """\
+            You are an intelligent assistant designed to provide accurate and relevant answers based on the provided context.
+
+            Rules:
+            - Always analyze the provided context thoroughly before answering.
+            - Respond with factual and concise information.
+            - If context is ambiguous or insufficient or you can't find answer, say 'I don't know.'
+            - Do not speculate or fabricate information beyond the provided context.
+            - Follow user instructions on the response style(default style is detailed response if user didn't provide any specifications):
+              - If the user asks for a detailed response, provide comprehensive explanations.
+              - If the user requests brevity, give concise and to-the-point answers.
+            - When applicable, summarize and synthesize information from the context to answer effectively.
+            - Avoid using information outside the given context.
+          """
+        context = self.retriever.hybrid_retrieve(question,
+                                                 enable_bm25=self.enable_bm25,
+                                                 enable_dense=self.enable_dense,
+                                                 enable_rerank=self.enable_rerank,
+                                                 top_k_bm25=self.top_k_bm25,
+                                                 top_n_dense=self.top_n_dense,
+                                                 top_n_rerank=self.top_n_rerank
+                                                 )
+
+        context_text = [doc['raw_text'] for doc in context]
+
+        response = completion(
+                                model=LLM_CORE_MODEL_NAME,
+                                temperature=0.0,
+                                messages=[
+                                    {"role": "system", "content": PROMPT},
+                                    {"role": "user", "content": f"Context: {context_text}\nQuestion: {question}"}
+                            ],
+                            api_key=GROQ_API_KEY
+                            )
+        return response, context
+
+    def form_response(self, question):
+      llm_response, context = self.__get_answer__(question)
+
+      metadata_raw = [doc['chapter_name'] for doc in context]
+      metadata_cleaned = [ast.literal_eval(item) for item in metadata_raw]
+
+      print('User:', question)
+      print('System:', llm_response.choices[0].message.content)
+
+      return f"**{llm_response.choices[0].message.content}**\n\nResources: {[chapter for doc in metadata_cleaned for chapter in doc]}"

chatbot/retriever.py

@@ -0,0 +1,132 @@
+from rank_bm25 import BM25Okapi
+import numpy as np
+import torch
+import re
+import string
+from sentence_transformers import SentenceTransformer, util, CrossEncoder
+
+
+DENSE_RETRIEVER_MODEL_NAME = "all-MiniLM-L6-v2"
+CROSS_ENCODER_MODEL_NAME = 'cross-encoder/ms-marco-MiniLM-L-12-v2'
+LLM_CORE_MODEL_NAME = "groq/llama3-8b-8192"
+
+
+def clean_text(text):
+    text = text.translate(str.maketrans('', '', string.punctuation))
+    text = text.lower()
+    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    text = re.sub(r'\s+', ' ', text)
+
+    return text.strip()
+
+
+class HybridRetrieverReranker:
+    def __init__(self, dataset, dense_model_name=DENSE_RETRIEVER_MODEL_NAME, cross_encoder_model=CROSS_ENCODER_MODEL_NAME):
+        if 'cleaned_text' not in dataset.columns:
+            raise ValueError("Dataset must contain a 'cleaned_text' column.")
+
+        self.dataset = dataset
+        self.bm25_corpus = dataset['cleaned_text'].tolist()
+        self.tokenized_corpus = [chunk.split() for chunk in self.bm25_corpus]
+        self.bm25 = BM25Okapi(self.tokenized_corpus)
+
+        self.dense_model = SentenceTransformer(dense_model_name)
+        self.cross_encoder = CrossEncoder(cross_encoder_model)
+
+
+    def bm25_retrieve(self, query, top_k=70):
+        """
+        Retrieve top K documents using BM25.
+
+        Args:
+            query (str): Query text.
+            top_k (int): Number of top BM25 documents to retrieve.
+
+        Returns:
+            list of dict: Top K BM25 results.
+        """
+        cleaned_query = clean_text(query)
+        query_tokens = cleaned_query.split()
+        bm25_scores = self.bm25.get_scores(query_tokens)
+        top_k_indices = np.argsort(bm25_scores)[::-1][:top_k]
+        return self.dataset.iloc[top_k_indices].to_dict(orient='records')
+
+
+    def dense_retrieve(self, query, candidates=None, top_n=35):
+        """
+        Retrieve top N documents using dense retrieval with LaBSE.
+
+        Args:
+            query (str): Query text.
+            candidates (list of dict): Candidate documents from BM25.
+            top_n (int): Number of top dense results to retrieve.
+
+        Returns:
+            list of dict: Top N dense results.
+        """
+        if candidates is None:
+            candidates = self.dataset.to_dict(orient='records')
+        query_embedding = self.dense_model.encode(query, convert_to_tensor=True)
+
+        candidate_embeddings = torch.stack([
+            eval(doc['chunk_embedding'].replace('tensor', 'torch.tensor')).clone().detach()
+            for doc in candidates
+        ])
+
+        similarities = util.pytorch_cos_sim(query_embedding, candidate_embeddings).squeeze(0)
+        top_n_indices = torch.topk(similarities, top_n).indices
+        return [candidates[idx] for idx in top_n_indices]
+
+
+    def rerank(self, query, candidates=None, top_n=3):
+        """
+        Rerank top documents using a CrossEncoder.
+
+        Args:
+            query (str): Query text.
+            candidates (list of dict): Candidate documents from dense retriever.
+            top_n (int): Number of top reranked results to return.
+
+        Returns:
+            list of dict: Top N reranked documents.
+        """
+        if candidates is None:
+            candidates = self.dataset.to_dict(orient='records')
+        query_document_pairs = [(query, doc['raw_text']) for doc in candidates]
+        scores = self.cross_encoder.predict(query_document_pairs)
+        top_n_indices = np.argsort(scores)[::-1][:top_n]
+        return [candidates[idx] for idx in top_n_indices]
+
+
+
+    def hybrid_retrieve(self, query, enable_bm25=True, enable_dense=True, enable_rerank=True, top_k_bm25=60, top_n_dense=30, top_n_rerank=2):
+        """
+        Perform hybrid retrieval: BM25 followed by dense retrieval and optional reranking.
+
+        Args:
+            query (str): Query text.
+            top_k_bm25 (int): Number of top BM25 documents to retrieve.
+            top_n_dense (int): Number of top dense results to retrieve.
+            enable_dense (bool): Whether dense retrieval should be enabled.
+            enable_rerank (bool): Whether reranking should be enabled.
+            top_n_rerank (int): Number of top reranked documents to return.
+
+        Returns:
+            list of dict: Final top results after hybrid retrieval and reranking.
+        """
+        if enable_bm25:
+            bm25_results = self.bm25_retrieve(query, top_k=top_k_bm25)
+        else:
+            bm25_results = None
+
+        if enable_dense:
+            dense_results = self.dense_retrieve(query, bm25_results, top_n=top_n_dense)
+        else:
+            dense_results = bm25_results
+
+        if enable_rerank:
+            final_results = self.rerank(query, dense_results, top_n=top_n_rerank)
+        else:
+            final_results = dense_results
+
+        return final_results

data/prepare_data.py

@@ -0,0 +1,66 @@
+import os
+import re
+import string
+from sentence_transformers import SentenceTransformer
+from langchain_text_splitters import CharacterTextSplitter
+import pandas as pd
+
+DATA_FILE_PATH = os.path.join(os.path.dirname(os.path.realpath(__file__)), "CountMonteCristoFull.txt")
+DENSE_RETRIEVER_MODEL_NAME = "all-MiniLM-L6-v2"
+CROSS_ENCODER_MODEL_NAME = 'cross-encoder/ms-marco-MiniLM-L-12-v2'
+LLM_CORE_MODEL_NAME = "groq/llama3-8b-8192"
+
+with open(DATA_FILE_PATH, "r", encoding="utf-8") as f:
+    data_corpus = f.read()
+
+splitter = CharacterTextSplitter(separator="\n\n", chunk_size=10_000, chunk_overlap=1_000)
+text_chunks = splitter.create_documents([data_corpus])
+
+prev_chapter_name = ''
+for chunk in text_chunks:
+    chunk.metadata['belongs_to'] = set()
+    curr_chapter_name = ''
+    index_start_chapter_name = chunk.page_content.find('Chapter')
+
+    if index_start_chapter_name == -1:
+        curr_chapter_name = prev_chapter_name
+    else:
+        # if prev_chapter_name is not empty and next chapter start further than first 40% of the chunk.
+        # This means that the name of the prev chapter isn't in this chunk, but relevant info can be found.
+        if prev_chapter_name != '' and index_start_chapter_name > int(len(chunk.page_content) * 0.4):
+            chunk.metadata['belongs_to'].add(prev_chapter_name)
+
+        index_end_chapter_name = chunk.page_content.find('\n\n', index_start_chapter_name)
+        curr_chapter_name = chunk.page_content[index_start_chapter_name:index_end_chapter_name]
+        prev_chapter_name = curr_chapter_name
+    chunk.metadata['belongs_to'].add(curr_chapter_name)
+
+    chunk.metadata['belongs_to'] = list(chunk.metadata['belongs_to'])
+
+
+def clean_text(text):
+    text = text.translate(str.maketrans('', '', string.punctuation))
+    text = text.lower()
+    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    text = re.sub(r'\s+', ' ', text)
+
+    return text.strip()
+
+dense_model = SentenceTransformer(DENSE_RETRIEVER_MODEL_NAME)
+
+def calculate_embeddings(text):
+    return dense_model.encode(text, convert_to_tensor=True)
+
+chunked_data_corpus = []
+
+for index, chunk in enumerate(text_chunks):
+    chunked_data_corpus.append({
+        'raw_text': chunk.page_content,
+        'cleaned_text': clean_text(chunk.page_content),
+        'chunk_embedding': calculate_embeddings(chunk.page_content),
+        'chapter_name': chunk.metadata['belongs_to']
+    })
+
+chunked_data_corpus_df = pd.DataFrame(chunked_data_corpus)
+
+chunked_data_corpus_df.to_csv('chunked_data_corpus.csv', index=False)

main.py

@@ -0,0 +1,31 @@
+import gradio as gr
+import pandas as pd
+from chatbot.bot import QuestionAnsweringBot
+import os
+
+chunked_data_corpus_df = pd.read_csv(os.path.join(os.path.dirname(os.path.realpath(__file__)), "data\\chunked_data_corpus.csv"))
+
+bot = QuestionAnsweringBot(chunked_data_corpus_df)
+
+def message_respond(message, history):
+    answer = bot.form_response(message)
+    return answer
+
+gr.ChatInterface(
+    fn=message_respond,
+    type="messages",
+    title="RAG System for 'The Count of Monte Cristo' book",
+    description="Here you can ask any questions in the context of the book 'The Count of Monte Cristo'. API key is already provided.",
+    theme=gr.themes.Monochrome(font='Lora', text_size='lg', radius_size='sm'),
+    examples=["Who is Monte Cristo?", 
+              "What is the title of Chapter 93", 
+              "Why Edmond Dantes was in prison?", 
+              "How many years does Edmon Dantes spent in prison?",
+              "Who said this sentence to whom 'Wait and hope_ (Fac et spera)'?",
+              "What is the title of Chapter 64?",
+              "Who is the president of the USA?",
+              "Who is the author of the book The Count of Monte Cristo?",
+              "Tell me about all the main identites in Monte Cristo?"
+              ],
+    cache_examples=False,
+).launch()