From 423fc50ecfe7adbd8cdee468ac74fd2929a8f595 Mon Sep 17 00:00:00 2001
From: Sebastian Raschka <mail@sebastianraschka.com>
Date: Mon, 20 May 2024 16:35:54 -0500
Subject: [PATCH 1/3] Add Stream API Example

---
 src/litserve/examples/simple_example.py | 34 +++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/src/litserve/examples/simple_example.py b/src/litserve/examples/simple_example.py
index 3d664df8..84cbec64 100644
--- a/src/litserve/examples/simple_example.py
+++ b/src/litserve/examples/simple_example.py
@@ -68,3 +68,37 @@ def predict(self, x):
     def encode_response(self, output):
         # float will take the output value directly onto CPU memory
         return {"output": float(output)}
+
+
+class SimpleStreamAPI(ls.LitAPI):
+    """
+    Run as:
+        ```
+        server = ls.LitServer(SimpleStreamAPI(), stream=True)
+        server.run(port=8000)
+        ```
+
+    Then, in a new Python session, retrieve the responses as follows:
+        ```
+        import requests
+        url = "http://127.0.0.1:8000/predict"
+
+        resp = requests.post(url, json={"input": "1, 2, 3]"}, headers=None, stream=True)
+        for line in resp.iter_content(5000):
+        if line:
+            print(line.decode("utf-8"))
+        ```
+    """
+    def setup(self, device) -> None:
+        self.model = lambda x: str(x)
+
+    def decode_request(self, request):
+        return request["input"]
+
+    def predict(self, x):
+        for i in range(10):
+            yield self.model(i)
+
+    def encode_response(self, output_stream):
+        for output in output_stream:
+            yield {"output": output}

From 8b17115363bb465e287393b1d9efa853857c9f75 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 20 May 2024 21:36:28 +0000
Subject: [PATCH 2/3] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 README.md                               | 6 +++---
 src/litserve/examples/simple_example.py | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 4dbb2f01..98efe46e 100644
--- a/README.md
+++ b/README.md
@@ -8,9 +8,9 @@
 **High-throughput serving engine for AI models**
 
 <pre>
-✅ Batching       ✅ Streaming          ✅ Auto-GPU, multi-GPU 
-✅ Multi-modal    ✅ PyTorch/JAX/TF     ✅ Full control        
-✅ Auth           ✅ Built on Fast API                         
+✅ Batching       ✅ Streaming          ✅ Auto-GPU, multi-GPU
+✅ Multi-modal    ✅ PyTorch/JAX/TF     ✅ Full control
+✅ Auth           ✅ Built on Fast API
 </pre>
 
 
diff --git a/src/litserve/examples/simple_example.py b/src/litserve/examples/simple_example.py
index 84cbec64..2fa0d76d 100644
--- a/src/litserve/examples/simple_example.py
+++ b/src/litserve/examples/simple_example.py
@@ -89,6 +89,7 @@ class SimpleStreamAPI(ls.LitAPI):
             print(line.decode("utf-8"))
         ```
     """
+
     def setup(self, device) -> None:
         self.model = lambda x: str(x)
 

From d13f4b707986c925bd43c40f7a96883632c72fbe Mon Sep 17 00:00:00 2001
From: Sebastian Raschka <mail@sebastianraschka.com>
Date: Mon, 20 May 2024 17:09:39 -0500
Subject: [PATCH 3/3] Modify example so it uses the requests.post input

---
 src/litserve/examples/simple_example.py | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/src/litserve/examples/simple_example.py b/src/litserve/examples/simple_example.py
index 2fa0d76d..26867db3 100644
--- a/src/litserve/examples/simple_example.py
+++ b/src/litserve/examples/simple_example.py
@@ -77,13 +77,11 @@ class SimpleStreamAPI(ls.LitAPI):
         server = ls.LitServer(SimpleStreamAPI(), stream=True)
         server.run(port=8000)
         ```
-
     Then, in a new Python session, retrieve the responses as follows:
         ```
         import requests
         url = "http://127.0.0.1:8000/predict"
-
-        resp = requests.post(url, json={"input": "1, 2, 3]"}, headers=None, stream=True)
+        resp = requests.post(url, json={"input": "Hello world"}, headers=None, stream=True)
         for line in resp.iter_content(5000):
         if line:
             print(line.decode("utf-8"))
@@ -91,14 +89,14 @@ class SimpleStreamAPI(ls.LitAPI):
     """
 
     def setup(self, device) -> None:
-        self.model = lambda x: str(x)
+        self.model = lambda x, y: f"{x}: {y}"
 
     def decode_request(self, request):
         return request["input"]
 
     def predict(self, x):
-        for i in range(10):
-            yield self.model(i)
+        for i in range(3):
+            yield self.model(i, x.encode("utf-8").decode())
 
     def encode_response(self, output_stream):
         for output in output_stream: