From 5d4d2e2c603e1b5301159132a0a29d61cfec490b Mon Sep 17 00:00:00 2001
From: Jeffrey Morgan <jmorganca@gmail.com>
Date: Sun, 10 Dec 2023 13:53:36 -0500
Subject: [PATCH] update docs with chat completion api

---
 README.md   | 5 +++--
 docs/api.md | 3 ++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index a8669fc5..d202d73e 100644
--- a/README.md
+++ b/README.md
@@ -205,7 +205,8 @@ Finally, in a separate shell, run a model:
 ## REST API
 
 Ollama has a REST API for running and managing models.
-For example, to generate text from a model:
+
+### Generate a response
 
 ```
 curl http://localhost:11434/api/generate -d '{
@@ -214,7 +215,7 @@ curl http://localhost:11434/api/generate -d '{
 }'
 ```
 
-Or send a chat message (coming in 0.1.14):
+### Chat with a model
 
 ```
 curl http://localhost:11434/api/chat -d '{
diff --git a/docs/api.md b/docs/api.md
index 248de114..5910ccf2 100644
--- a/docs/api.md
+++ b/docs/api.md
@@ -3,6 +3,7 @@
 ## Endpoints
 
 - [Generate a completion](#generate-a-completion)
+- [Generate a chat completion](#generate-a-chat-completion)
 - [Create a Model](#create-a-model)
 - [List Local Models](#list-local-models)
 - [Show Model Information](#show-model-information)
@@ -290,7 +291,7 @@ curl http://localhost:11434/api/generate -d '{
 }
 ```
 
-## Send Chat Messages (coming in 0.1.14)
+## Generate a chat completion
 
 ```shell
 POST /api/chat