diff --git a/pyproject.toml b/pyproject.toml
index 77187023..15c61268 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -6,7 +6,8 @@ authors = ["Relevance Team <relevance@pinecone.io>"]
 readme = "README.md"
 license = "Apache-2.0"
 packages = [{include = "canopy", from = "src"},
-            {include = "canopy_cli", from = "src"},]
+            {include = "canopy_cli", from = "src"},
+            {include = "canopy_server", from = "src"},]
 
 [tool.poetry.dependencies]
 python = "^3.9"
diff --git a/src/canopy_cli/cli.py b/src/canopy_cli/cli.py
index 7fcf8757..bee46cfe 100644
--- a/src/canopy_cli/cli.py
+++ b/src/canopy_cli/cli.py
@@ -28,9 +28,9 @@
 
 from canopy import __version__
 
-from .app import start as start_service
+from canopy_server.app import start as start_service
 from .cli_spinner import Spinner
-from .api_models import ChatDebugInfo
+from canopy_server.api_models import ChatDebugInfo
 
 
 load_dotenv()
@@ -479,7 +479,7 @@ def start(host: str, port: str, reload: bool, config: Optional[str]):
         "🚨 Note 🚨\n"
         "For debugging only. To run the Canopy service in production, run the command:"
         "\n"
-        "gunicorn canopy_cli.app:app --worker-class uvicorn.workers.UvicornWorker "
+        "gunicorn canopy_server.app:app --worker-class uvicorn.workers.UvicornWorker "
         f"--bind {host}:{port} --workers <num_workers>"
     )
     for c in note_msg:
@@ -504,7 +504,7 @@ def start(host: str, port: str, reload: bool, config: Optional[str]):
               help="URL of the Canopy service to use. Defaults to http://0.0.0.0:8000")
 def stop(url):
     # Check if the service was started using Gunicorn
-    res = subprocess.run(["pgrep", "-f", "gunicorn canopy_cli.app:app"],
+    res = subprocess.run(["pgrep", "-f", "gunicorn canopy_server.app:app"],
                          capture_output=True)
     output = res.stdout.decode("utf-8").split()
 
@@ -514,7 +514,7 @@ def stop(url):
                "Do you want to kill all Gunicorn processes?")
         click.confirm(click.style(msg, fg="red"), abort=True)
         try:
-            subprocess.run(["pkill", "-f", "gunicorn canopy_cli.app:app"], check=True)
+            subprocess.run(["pkill", "-f", "gunicorn canopy_server.app:app"], check=True)
         except subprocess.CalledProcessError:
             try:
                 [os.kill(int(pid), signal.SIGINT) for pid in output]
diff --git a/src/canopy_server/__init__.py b/src/canopy_server/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/canopy_cli/api_models.py b/src/canopy_server/api_models.py
similarity index 100%
rename from src/canopy_cli/api_models.py
rename to src/canopy_server/api_models.py
diff --git a/src/canopy_cli/app.py b/src/canopy_server/app.py
similarity index 97%
rename from src/canopy_cli/app.py
rename to src/canopy_server/app.py
index c2f54903..a135754c 100644
--- a/src/canopy_cli/app.py
+++ b/src/canopy_server/app.py
@@ -25,9 +25,9 @@
 
 from canopy.models.api_models import StreamingChatResponse, ChatResponse
 from canopy.models.data_models import Context
-from canopy_cli.api_models import \
-    ChatRequest, ContextQueryRequest, \
-    ContextUpsertRequest, HealthStatus, ContextDeleteRequest
+from .api_models import \
+     ChatRequest, ContextQueryRequest, \
+     ContextUpsertRequest, HealthStatus, ContextDeleteRequest
 
 from canopy.llm.openai import OpenAILLM
 from canopy_cli.errors import ConfigError
@@ -260,7 +260,7 @@ def start(host="0.0.0.0", port=8000, reload=False, config_file=None):
     if config_file:
         os.environ["CANOPY_CONFIG_FILE"] = config_file
 
-    uvicorn.run("canopy_cli.app:app", host=host, port=port, reload=reload, workers=0)
+    uvicorn.run("canopy_server.app:app", host=host, port=port, reload=reload, workers=0)
 
 
 if __name__ == "__main__":
diff --git a/tests/e2e/test_app.py b/tests/e2e/test_app.py
index 6bcf191c..b37af3e6 100644
--- a/tests/e2e/test_app.py
+++ b/tests/e2e/test_app.py
@@ -10,9 +10,9 @@
 
 from canopy.knowledge_base import KnowledgeBase
 
-from canopy_cli.app import app
-from canopy_cli.api_models import (HealthStatus, ContextUpsertRequest,
-                                   ContextQueryRequest)
+from canopy_server.app import app
+from canopy_server.api_models import (HealthStatus, ContextUpsertRequest,
+                                      ContextQueryRequest)
 from .. import Tokenizer
 
 upsert_payload = ContextUpsertRequest(