README notice about api endpoint

1ec92b731efa57b1ac87ea57a3cf397247104cb0 · 2024-07-15 22:46:06 -0700 · Alex Cheema

Files touched

M README.md

Diff

commit 1ec92b731efa57b1ac87ea57a3cf397247104cb0
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Mon Jul 15 22:46:06 2024 -0700

    README notice about api endpoint
---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 21297ff3..48392bbf 100644
--- a/README.md
+++ b/README.md
@@ -74,9 +74,9 @@ python3 main.py
 
 That's it! No configuration required - exo will automatically discover the other device(s).
 
-A ChatGPT-like web interface will be available on each device on port 8000 http://localhost:8000.
+Until the below is fixed, the only way to access inference is via peer handles. See how it's done in [this example for Llama 3](examples/llama3_distributed.py).
 
-An API endpoint will be available on port 8001. Example usage:
+// A ChatGPT-like web interface will be available on each device on port 8000 http://localhost:8000 and Chat-GPT-compatible API on port 8001 (currently doesn't work see https://github.com/exo-explore/exo/issues/6).
 
 ```sh
 curl -X POST http://localhost:8001/api/v1/chat -H "Content-Type: application/json" -d '{"messages": [{"role": "user", "content": "What is the meaning of life?"}]}'

← 108a904a Readme whitespace · back to Exo · (partially) restore exo node equality by forwarding prompts 1d5c28ae →