From a28b8c81a88c2c09ec1a09a1b1b4d158a71be71a Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Sun, 13 Oct 2024 19:18:36 +0300
Subject: [PATCH] server : update readme [no ci]

---
 examples/server/README.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/examples/server/README.md b/examples/server/README.md
index cd0eaf847..62251b232 100644
--- a/examples/server/README.md
+++ b/examples/server/README.md
@@ -524,6 +524,12 @@ Takes a prefix and a suffix and returns the predicted completion as stream.
 
 - `input_prefix`: Set the prefix of the code to infill.
 - `input_suffix`: Set the suffix of the code to infill.
+- `prompt`: Added after the `FIM_MID` token
+- `extra_context`: Additional context inserted before the FIM prefix. See https://github.com/ggerganov/llama.cpp/pull/9874
+
+```txt
+[extra_context]<FIM_PRE>[input_prefix]<FIM_SUF>[input_suffix]<FIM_MID>[prompt]
+```
 
 It also accepts all the options of `/completion`.