diff --git a/data/datasets/medium_articles_posts/README.md b/data/datasets/medium_articles_posts/README.md
new file mode 100644
index 0000000000..1b915cc296
--- /dev/null
+++ b/data/datasets/medium_articles_posts/README.md
@@ -0,0 +1,45 @@
+# Medium Articles Posts Dataset
+
+## Description
+
+The Medium Articles Posts dataset contains a collection of articles published on
+the Medium platform. Each article entry includes information such as the
+article's title, main content or text, associated URL or link, authors' names,
+timestamps, and tags or categories.
+
+## Dataset Info
+
+The dataset consists of the following features:
+
+- **title**: _(string)_ The title of the Medium article.
+- **text**: _(string)_ The main content or text of the Medium article.
+- **url**: _(string)_ The URL or link to the Medium article.
+- **authors**: _(string)_ The authors or contributors of the Medium article.
+- **timestamp**: _(string)_ The timestamp or date when the Medium article was
+  published.
+- **tags**: _(string)_ Tags or categories associated with the Medium article.
+
+## Dataset Size
+
+- **Total Dataset Size**: 1,044,746,687 bytes (approximately 1000 MB)
+
+## Splits
+
+The dataset is split into the following part:
+
+- **Train**:
+  - Number of examples: 192,368
+  - Size: 1,044,746,687 bytes (approximately 1000 MB)
+
+## Download Size
+
+- **Compressed Download Size**: 601,519,297 bytes (approximately 600 MB)
+
+### Usage example
+
+```python
+from datasets import load_dataset
+#Load the dataset
+dataset = load_dataset("Falah/medium_articles_posts")
+
+```
diff --git a/data/datasets/medium_articles_posts/__init__.py b/data/datasets/medium_articles_posts/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/data/datasets/medium_articles_posts/load_dataset.py b/data/datasets/medium_articles_posts/load_dataset.py
new file mode 100644
index 0000000000..d8b750a3b8
--- /dev/null
+++ b/data/datasets/medium_articles_posts/load_dataset.py
@@ -0,0 +1,4 @@
+from datasets import load_dataset
+
+# Load the dataset
+dataset = load_dataset("Falah/medium_articles_posts")
diff --git a/data/datasets/medium_articles_posts/requirements.txt b/data/datasets/medium_articles_posts/requirements.txt
new file mode 100644
index 0000000000..76de43c3ed
--- /dev/null
+++ b/data/datasets/medium_articles_posts/requirements.txt
@@ -0,0 +1 @@
+datasets==2.9.0
diff --git a/data/datasets/research_papers_dataset/ReadME.md b/data/datasets/research_papers_dataset/ReadME.md
new file mode 100644
index 0000000000..6dd05432a2
--- /dev/null
+++ b/data/datasets/research_papers_dataset/ReadME.md
@@ -0,0 +1,139 @@
+---
+dataset_info:
+  features:
+    - name: title
+      dtype: string
+    - name: abstract
+      dtype: string
+  splits:
+    - name: train
+      num_bytes: 2363569633
+      num_examples: 2311491
+  download_size: 1423881564
+  dataset_size: 2363569633
+---
+
+<!-- markdownlint-disable -->
+
+## Research Paper Dataset 2023
+
+[Check out this website](https://huggingface.co/datasets/Falah/research_paper2023)
+
+### Dataset Information
+
+The "Research Paper Dataset 2023" contains information related to research
+papers. It includes the following features:
+
+- Title (dtype: string): The title of the research paper.
+- Abstract (dtype: string): The abstract of the research paper.
+
+### Dataset Splits
+
+The dataset is divided into one split:
+
+- Train Split:
+  - Name: train
+  - Number of Bytes: 2,363,569,633
+  - Number of Examples: 2,311,491
+
+### Download Information
+
+- Download Size: 1,423,881,564 bytes
+- Dataset Size: 2,363,569,633 bytes
+
+### Dataset Citation
+
+If you use this dataset in your research or project, please cite it as follows:
+
+```
+@dataset{Research Paper Dataset 2023,
+  author = {Falah.G.Salieh},
+  title = {Research Paper Dataset 2023,},
+  year = {2023},
+  publisher = {Hugging Face},
+  version = {1.0},
+  location = {Online},
+  url = {Falah/research_paper2023}
+}
+
+
+```
+
+### Apache License
+
+The "Research Paper Dataset 2023" is distributed under the Apache License 2.0.
+You can find a copy of the license in the LICENSE file of the dataset
+repository.
+
+The specific licensing and usage terms for this dataset can be found in the
+dataset repository or documentation. Please make sure to review and comply with
+the applicable license and usage terms before downloading and using the dataset.
+
+### Example Usage
+
+To load the "Research Paper Dataset 2023" using the Hugging Face Datasets
+Library in Python, you can use the following code:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("Falah/research_paper2023")
+```
+
+### Application of "Research Paper Dataset 2023" for NLP Text Classification and Chatbot Models
+
+The "Research Paper Dataset 2023" can be a valuable resource for various Natural
+Language Processing (NLP) tasks, including text classification and generating
+titles for books in the context of chatbot models. Here are some ways this
+dataset can be utilized for these applications:
+
+1. **Text Classification**: The dataset's features, such as the title and
+   abstract of research papers, can be used to train a text classification
+   model. By assigning appropriate labels to the research papers based on their
+   topics or fields of study, the model can learn to classify new research
+   papers into different categories. For example, the model can predict whether
+   a research paper is related to computer science, biology, physics, etc. This
+   text classification model can then be adapted for other applications that
+   require categorizing text.
+
+2. **Book Title Generation for Chatbot Models**: By utilizing the research paper
+   titles in the dataset, a natural language generation model, such as a
+   sequence-to-sequence model or a transformer-based model, can be trained to
+   generate book titles. The model can be fine-tuned on the research paper
+   titles to learn patterns and structures in generating relevant and meaningful
+   book titles. This can be a useful feature for chatbot models that recommend
+   books based on specific research topics or areas of interest.
+
+### Potential Benefits
+
+- Improved Chatbot Recommendations: With the ability to generate book titles
+  related to specific research topics, chatbot models can provide more relevant
+  and personalized book recommendations to users.
+- Enhanced User Engagement: By incorporating the text classification model, the
+  chatbot can better understand user queries and respond more accurately,
+  leading to a more engaging user experience.
+- Knowledge Discovery: Researchers and students can use the text classification
+  model to efficiently categorize large collections of research papers, enabling
+  quicker access to relevant information in specific domains.
+
+### Considerations
+
+- Data Preprocessing: Before training the NLP models, appropriate data
+  preprocessing steps may be required, such as text cleaning, tokenization, and
+  encoding, to prepare the dataset for model input.
+- Model Selection and Fine-Tuning: Choosing the right NLP model architecture and
+  hyperparameters, and fine-tuning the model on the specific tasks, can
+  significantly impact the model's performance and generalization ability.
+- Ethical Use: Ensure that the generated book titles and text classification
+  predictions are used responsibly and ethically, respecting copyright and
+  intellectual property rights.
+
+### Conclusion
+
+The "Research Paper Dataset 2023" holds great potential for enhancing NLP text
+classification models and chatbot systems. By leveraging the dataset's features
+and information, NLP applications can be developed to aid researchers, students,
+and readers in finding relevant research papers and generating meaningful book
+titles for their specific interests. Proper utilization of this dataset can lead
+to more efficient information retrieval and improved user experiences in the
+domain of research and academic literature exploration.
diff --git a/data/datasets/research_papers_dataset/__init__.py b/data/datasets/research_papers_dataset/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/data/datasets/research_papers_dataset/load_dataset.py b/data/datasets/research_papers_dataset/load_dataset.py
new file mode 100644
index 0000000000..4602f0d253
--- /dev/null
+++ b/data/datasets/research_papers_dataset/load_dataset.py
@@ -0,0 +1,3 @@
+from datasets import load_dataset
+
+dataset = load_dataset("Falah/research_paper2023")
diff --git a/data/datasets/research_papers_dataset/requirements.txt b/data/datasets/research_papers_dataset/requirements.txt
new file mode 100644
index 0000000000..76de43c3ed
--- /dev/null
+++ b/data/datasets/research_papers_dataset/requirements.txt
@@ -0,0 +1 @@
+datasets==2.9.0
diff --git a/data/datasets/sentiments-dataset-381-classes/README.md b/data/datasets/sentiments-dataset-381-classes/README.md
new file mode 100644
index 0000000000..6d4983e27a
--- /dev/null
+++ b/data/datasets/sentiments-dataset-381-classes/README.md
@@ -0,0 +1,363 @@
+---
+dataset_info:
+  features:
+    - name: text
+      dtype: string
+    - name: sentiment
+      dtype: string
+  splits:
+    - name: train
+      num_bytes: 104602
+      num_examples: 1061
+  download_size: 48213
+  dataset_size: 104602
+license: apache-2.0
+task_categories:
+  - text-classification
+language:
+  - en
+pretty_name: sentiments-dataset-381-classes
+size_categories:
+  - 1K<n<10K
+---
+
+<!-- markdownlint-disable -->
+
+# Sentiments Dataset (381 Classes)
+
+## Dataset Description
+
+This dataset contains a collection of labeled sentences categorized into 381
+different sentiment classes. The dataset provides a wide range of sentiment
+labels to facilitate fine-grained sentiment analysis tasks. Each sentence is
+associated with a sentiment class name.
+
+## Dataset Information
+
+- Number of classes: 381
+- Features: `text` (string), `sentiment` (string)
+- Number of examples: 1,061
+
+## Class Names
+
+The dataset includes the following sentiment class names as examples:
+
+- Positive
+- Negative
+- Neutral
+- Joyful
+- Disappointed
+- Worried
+- Surprised
+- Grateful
+- Indifferent
+- Sad
+- Angry
+- Relieved
+- Sentiment
+- Excited
+- Hopeful
+- Anxious
+- Satisfied
+- Happy
+- Nostalgic
+- Inspired
+- Impressed
+- Amazed
+- Touched
+- Proud
+- Intrigued
+- Relaxed
+- Content
+- Comforted
+- Motivated
+- Frustrated
+- Delighted
+- Moved
+- Curious
+- Fascinated
+- Engrossed
+- Addicted
+- Eager
+- Provoked
+- Energized
+- Controversial
+- Significant
+- Revolutionary
+- Optimistic
+- Impactful
+- Compelling
+- Enchanted
+- Peaceful
+- Disillusioned
+- Thrilled
+- Consumed
+- Engaged
+- Trendy
+- Informative
+- Appreciative
+- Enthralled
+- Enthusiastic
+- Influenced
+- Validated
+- Reflective
+- Emotional
+- Concerned
+- Promising
+- Empowered
+- Memorable
+- Transformative
+- Inclusive
+- Groundbreaking
+- Evocative
+- Respectful
+- Outraged
+- Unity
+- Enlightening
+- Artistic
+- Cultural
+- Diverse
+- Vibrant
+- Prideful
+- Captivated
+- Revealing
+- Inspiring
+- Admiring
+- Empowering
+- Connecting
+- Challenging
+- Symbolic
+- Immersed
+- Evolving
+- Insightful
+- Reformative
+- Celebratory
+- Validating
+- Diversity
+- Eclectic
+- Comprehensive
+- Uniting
+- Influential
+- Honoring
+- Transporting
+- Resonating
+- Chronicle
+- Preserving
+- Replicated
+- Impressive
+- Fascinating
+- Tributary
+- Momentum
+- Awe-inspiring
+- Unearthing
+- Exploratory
+- Immersive
+- Transportive
+- Personal
+- Resilient
+- Mesmerized
+- Legendary
+- Awareness
+- Evidence-based
+- Contemporary
+- Connected
+- Valuable
+- Referencing
+- Camaraderie
+- Inspirational
+- Evoke
+- Emotive
+- Chronicling
+- Educational
+- Serene
+- Colorful
+- Melodious
+- Dramatic
+- Enlivened
+- Wonderstruck
+- Enchanting
+- Grandiose
+- Abundant
+- Harmonious
+- Captivating
+- Mesmerizing
+- Dedicated
+- Powerful
+- Mystical
+- Picturesque
+- Opulent
+- Revitalizing
+- Fragrant
+- Spellbinding
+- Lush
+- Breathtaking
+- Passionate
+- Melodic
+- Wonderland
+- Invigorating
+- Dappled
+- Flourishing
+- Ethereal
+- Elaborate
+- Kaleidoscope
+- Harmonizing
+- Tragic
+- Transforming
+- Marveling
+- Enveloped
+- Reverberating
+- Sanctuary
+- Graceful
+- Spectacular
+- Golden
+- Melancholic
+- Transcendent
+- Delicate
+- Awakening
+- Intertwined
+- Indelible
+- Verdant
+- Heartrending
+- Fiery
+- Inviting
+- Majestic
+- Lullaby-like
+- Kissed
+- Behold
+- Soulful
+- Splendid
+- Whispering
+- Masterpiece
+- Moving
+- Crystalline
+- Tapestry
+- Haunting
+- Renewal
+- Wisdom-filled
+- Stunning
+- Sun-kissed
+- Symphony
+- Awestruck
+- Dancing
+- Heart-wrenching
+- Magical
+- Gentle
+- Emotion-evoking
+- Embracing
+- Floating
+- Tranquil
+- Celestial
+- Breathless
+- Symphonic
+- Stillness
+- Delightful
+- Flawless
+- Commanding
+- Embraced
+- Heartfelt
+- Precise
+- Adorned
+- Beautiful
+- Scattering
+- Timeless
+- Radiant
+- Regal
+- Sparkling
+- Resilience
+- Recognized
+- Echoing
+- Rebirth
+- Cradled
+- Tirelessly
+- Glowing
+- Icy
+- Brilliant
+- Anticipation
+- Awakened
+- Blossoming
+- Enthralling
+- Excitement
+- Vivid
+- Spellbound
+- Mellifluous
+- Intricate
+- Silent
+- Contrasting
+- Poignant
+- Perfumed
+- Pure
+- Magnificent
+- Exquisite
+- Anguished
+- Harmonic
+- Kaleidoscopic
+- Gripping
+- Soothing
+- Intense
+- Poetic
+- Fragile
+- Unwavering
+- Intriguing
+- Fairy-tale
+- Ephemeral
+- Joyous
+- Resplendent
+- Elegant
+- Coaxing
+- Illuminating
+- Thunderous
+- Cool
+- Exciting
+- Teeming
+- Blissful
+- Enduring
+- Raw
+- Adventurous
+- Mysterious
+- Enrapturing
+- Marvelous
+- Swirling
+- Resonant
+- Careful
+- Whimsical
+- Intertwining
+- - and more
+
+## Usage example
+
+```python
+from datasets import load_dataset
+#Load the dataset
+dataset = load_dataset("Falah/sentiments-dataset-381-classes")
+#Convert the dataset to a pandas DataFrame
+df = pd.DataFrame(dataset['train'])
+#Get the unique class names from the "sentiment" column
+class_names = df['sentiment'].unique()
+#Print the unique class names
+for name in class_names:
+    print(f"Class Name: {name}")
+
+```
+
+## Application
+
+The Sentiments Dataset (381 Classes) can be applied in various NLP applications,
+such as sentiment analysis and text classification.
+
+## Citation
+
+If you use this dataset in your research or publication, please cite it as
+follows:
+
+For more information or inquiries about the dataset, please contact the dataset
+author(s) mentioned in the citation.
+
+```
+@dataset{sentiments_dataset_381_classes),
+  author = {Falah.G.Salieh},
+  title = {Sentiments Dataset (381 Classes)},
+  year = {2023},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/datasets/Falah/sentiments-dataset-381-classes},
+}
+```
diff --git a/data/datasets/sentiments-dataset-381-classes/__init__.py b/data/datasets/sentiments-dataset-381-classes/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/data/datasets/sentiments-dataset-381-classes/load_dataset.py b/data/datasets/sentiments-dataset-381-classes/load_dataset.py
new file mode 100644
index 0000000000..f7200c1656
--- /dev/null
+++ b/data/datasets/sentiments-dataset-381-classes/load_dataset.py
@@ -0,0 +1,3 @@
+from datasets import load_dataset
+
+dataset = load_dataset("Falah/sentiments-dataset-381-classes")
diff --git a/data/datasets/sentiments-dataset-381-classes/requirements.txt b/data/datasets/sentiments-dataset-381-classes/requirements.txt
new file mode 100644
index 0000000000..76de43c3ed
--- /dev/null
+++ b/data/datasets/sentiments-dataset-381-classes/requirements.txt
@@ -0,0 +1 @@
+datasets==2.9.0