From d7465d2e84de16aa4620787ddfdca2258c452bde Mon Sep 17 00:00:00 2001
From: goldpulpy <sawsani1928@gmail.com>
Date: Wed, 9 Oct 2024 02:32:21 +0300
Subject: [PATCH] UPDATE: Readme

---
 README.md | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 54 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index 6dad40a..bf5e7ef 100644
--- a/README.md
+++ b/README.md
@@ -84,7 +84,7 @@ embeddings = model.encode(sentences, progress_bar=True)
 # The rounding parameter allows us to round our float values
 # with a default of 2, which means 2 decimal places.
 compute_score(source_embedding, embeddings)
-# Output: [0.86, 0.77, 0.48]
+# Return: [0.86, 0.77, 0.48]
 ```
 
 `compute_score` returns in the same index order in which the embedding was encoded.
@@ -110,7 +110,7 @@ You can use the computational functions: `cosine`, `euclidean`, `manhattan`, `ja
 from pysentence_similarity.compute import euclidean
 
 compute_score(source_embedding, embeddings, compute_function=euclidean)
-## Output: [2.52, 3.28, 5.62]
+# Return: [2.52, 3.28, 5.62]
 ```
 
 You can use `max_pooling`, `mean_pooling`, `min_pooling` or your custom function
@@ -128,22 +128,71 @@ embeddings = model.encode(sentences, pooling_function=max_pooling)
 ```python
 from pysentence_similarity import Splitter
 
-# Default split symbols: '\n'
+# Default split markers: '\n'
 splitter = Splitter()
 
 # If you want to separate by specific characters.
-splitter = Splitter(split_symbols='.!?')
+splitter = Splitter(split_markers=["!", "?", "."], keep_markers=True)
 
 # Test text
 text = "Hello world! How are you? I'm fine."
 
 # Split from text
 splitter.split_from_text(text)
-# Output: ['Hello world!', 'How are you?', "I'm fine."]
+# Return: ['Hello world!', 'How are you?', "I'm fine."]
 ```
 
 At this point, sources for the splitting are available: text, file, URL, CSV, and JSON.
 
+### Storage 💾
+
+The storage allows you to save and link sentences and their embeddings for easy access, so you don't need to encode a large corpus of text every time. The storage also enables similarity searching.
+
+The storage must store the **sentences** themselves and their **embeddings**.
+
+```python
+from pysentence_similarity import Model, Storage
+
+# Create an instance of the model
+model = Model("all-MiniLM-L6-v2", dtype="fp16")
+
+# Create an instance of the storage
+storage = Storage()
+sentences = [
+    "This is another test.",
+    "This is yet another test.",
+    "We are testing sentence similarity."
+]
+
+# Convert sentences to embeddings
+embeddings = model.encode(sentences)
+
+# Add sentences and their embeddings
+storage.add(sentences, embeddings)
+
+# Save the storage
+storage.save("my_storage.h5")
+```
+
+Load embeddings from the storage
+
+```python
+from pysentence_similarity import Model, Storage, compute_score
+
+# Create an instance of the model and storage
+model = Model("all-MiniLM-L6-v2", dtype="fp16")
+storage = Storage.load("my_storage.h5")
+
+# Convert sentence to embedding
+source_embedding = model.encode("This is a test.")
+
+# Compute similarity scores with the storage
+compute_score(source_embedding, storage)
+# Return: [0.86, 0.77, 0.48]
+```
+
 ## License 📜
 
 This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details
+
+<h6 align="center">Created by goldpulpy with ❤️</h6>