updates

docs/index.rst

@@ -3,9 +3,9 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-.. image:: Logo-scaled.png
+.. image:: logo_with_text.png
    :width: 300px
-   :height: 175px
+   :height: 170px
    :align: center
 
 LOTUS Makes LLM-Powerd Data Processing Fast and Easy

docs/installation.rst

@@ -18,4 +18,16 @@ You can install Lotus using pip:
 
     $ conda create -n lotus python=3.10 -y
     $ conda activate lotus
-    $ pip install lotus-ai
+    $ pip install lotus-ai
+
+After you must install Faiss via conda:
+
+.. code-block:: console
+
+    # CPU-only version
+    $ conda install -c pytorch faiss-cpu=1.9.0
+
+    # GPU(+CPU) version
+    $ conda install -c pytorch -c nvidia faiss-gpu=1.9.0
+
+For more details, see `Installing FAISS via Conda <https://github.com/facebookresearch/faiss/blob/main/INSTALL.md#installing-faiss-via-conda>`_.

docs/sem_index.rst

@@ -5,6 +5,17 @@ sem_index
     :members:
     :show-inheritance:
 
+Overview
+---------
+The sem_index operator in LOTUS creates a semantic index for a given column in a DataFrame. 
+This index enables efficient retrieval and ranking of records based on semantic similarity, making 
+it easier to query and analyze large datasets with natural language or contextual search criteria. 
+
+Motivation
+-----------
+Traditional search techniques struggle with context-dependent queries or subtle semantic nuances. 
+The sem_index operator addresses this by leveraging language models to create an index that supports semantic search
+
 Example
 ----------
 .. code-block:: python
@@ -76,3 +87,8 @@ Output:
 | 13 | Introduction to Computer Networks           |
 +----+---------------------------------------------+
 
+
+Required Parameters
+--------------------
+- **col_name** : The column name to index.
+- **index_dir** : The directory to save the index.

docs/sem_partition.rst

@@ -5,6 +5,20 @@ sem_partition_by
     :members:
     :show-inheritance:
 
+Overview
+---------
+The sem_partition_by operator in LOTUS enables semantic partitioning of data based on contextual similarities. 
+It divides a DataFrame into subsets, which can then be independently analyzed or aggregated.  This operator works 
+seamlessly with other LOTUS components, like sem_index for creating embeddings and sem_agg for performing 
+aggregations on clustered subsets, to build scalable and efficient workflows.
+
+Motivation
+----------
+Real-world data often requires grouping based on meaning rather than exact matches, which traditional methods GROUP BY 
+cannot handle. The sem_partition_by operator solves this by clustering data semantically, allowing for 
+meaningful partitioning of natural language or context-dependent entries.
+
+
 Example
 ----------
 .. code-block:: python
@@ -33,3 +47,9 @@ Example
     out = df.sem_agg("Summarize all {Course Name}")._output[0]
     print(out)
 
+
+Required Parameters
+--------------------
+- **partition_fn** : The partitioning function.
+
+