Add option for local model, instead of downloading it every time.

.gitignore

@@ -48,4 +48,8 @@ var/
 # pytest
 *pytest_cache
 
+# Credentials
 key_openai.txt
+
+# Models saved locally
+models/

README.md

@@ -36,6 +36,50 @@ To run REMO, you will need the following:
 2. Interact with the API using a REST client or web browser: `http://localhost:8000`
 
 
+## Models
+
+### Embedding Model
+
+REMO currently uses the
+Universal Sentence Encoder v5 for generating embeddings.
+
+#### Loading from TensorFlow Hub
+
+This is the default option.
+
+When 
+
+```python
+ARE_YOU_TESTING__LOAD_MODEL_LOCAL = False
+```
+
+in file `utils.py`, the model is loaded from TensorFlow Hub.
+
+#### Loading from a local file
+
+Downloading the model from TensorFlow Hub every time you need to spin up
+the microservice would be expensive and time-consuming.
+
+1. Download the `.tar.gz` file from
+   TensorFlow Hub: https://tfhub.dev/google/universal-sentence-encoder-large/5
+
+   ![img.png](docs/images/embedding_local_1.png)
+
+2. Extract the file to the folder
+   ```
+   models/universal-sentence-encoder-large_5/
+   ```
+   with
+   ```shell
+   tar -xvzf universal-sentence-encoder-large_5.tar.gz
+   ```
+
+3. Set
+   ```python
+   ARE_YOU_TESTING__LOAD_MODEL_LOCAL = True
+   ```
+   in file `utils.py`.
+
 ## API Endpoints
 
 - **POST /add_message**: Add a new message to REMO. Speaker, timestamp, and content required.

remo.py

@@ -1,42 +1,55 @@
 from fastapi import FastAPI
 import utils
 import os
+import uvicorn
 
 app = FastAPI()
 root_folder = os.getcwd()
-#root_folder = 'C:/raven_private/REMO/'
+# root_folder = 'C:/raven_private/REMO/'
 max_cluster_size = 5
 # REMO = Rolling Episodic Memory Organizer
 
+
 @app.post("/add_message")
-async def add_message(message: str, speaker: str, timestamp: float):
+async def add_message(
+    message: str,
+    speaker: str,
+    timestamp: float,
+):
     # Add message to REMO
     new_message = utils.create_message(message, speaker, timestamp)
-    print('\n\nADD MESSAGE -', new_message)
+    print("\n\nADD MESSAGE -", new_message)
     utils.save_message(root_folder, new_message)
 
     return {"detail": "Message added"}
 
+
 @app.get("/search")
 async def search(query: str):
     # Search the tree for relevant nodes
-    print('\n\nSEARCH -', query)
+    print("\n\nSEARCH -", query)
     taxonomy = utils.search_tree(root_folder, query)
 
     return {"results": taxonomy}
 
+
 @app.post("/rebuild_tree")
 async def rebuild_tree():
     # Trigger full tree rebuilding event
-    print('\n\nREBUILD TREE')
+    print("\n\nREBUILD TREE")
     utils.rebuild_tree(root_folder, max_cluster_size)
 
     return {"detail": "Tree rebuilding completed"}
 
+
 @app.post("/maintain_tree")
 async def maintain_tree():
     # Trigger tree maintenance event
-    print('\n\nMAINTAIN TREE')
+    print("\n\nMAINTAIN TREE")
     utils.maintain_tree(root_folder)
 
     return {"detail": "Tree maintenance completed"}
+
+
+if __name__ == '__main__':
+    uvicorn.run(app, host='0.0.0.0', port=8000)