From 492f42b572248063a529ce3cff54a8bde55d96e4 Mon Sep 17 00:00:00 2001
From: Omkar Bhoir <71968255+omkar787@users.noreply.github.com>
Date: Thu, 25 Apr 2024 22:30:00 +0530
Subject: [PATCH] Note added in readme about the fact that the ollama service
 should be running before using ollama python library and also details about
 how to solve the connection refused error while running ollama in a jupyter
 notebook is also added

---
 README.md | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/README.md b/README.md
index 2864917..ed71866 100644
--- a/README.md
+++ b/README.md
@@ -21,6 +21,23 @@ response = ollama.chat(model='llama2', messages=[
 print(response['message']['content'])
 ```
 
+### Note
+To start using this library, you need to have ollama running on your system. If you are running ollama on a jupyter notebook, then you can use the below code to fix the "connection refused" error
+
+```python
+import os
+import threading
+import subprocess
+
+def ollama():
+    os.environ['OLLAMA_HOST'] = '0.0.0.0:11434'
+    os.environ['OLLAMA_ORIGINS'] = '*'
+    subprocess.Popen(["ollama", "serve"])
+
+ollama_thread = threading.Thread(target=ollama)
+ollama_thread.start()
+```
+
 ## Streaming responses
 
 Response streaming can be enabled by setting `stream=True`, modifying function calls to return a Python generator where each part is an object in the stream.