diff --git a/.github/workflows/llmsecops-cicd.llm.yml b/.github/workflows/llmsecops-cicd.llm.yml
index 29c411e79..be9ece60d 100644
--- a/.github/workflows/llmsecops-cicd.llm.yml
+++ b/.github/workflows/llmsecops-cicd.llm.yml
@@ -33,9 +33,9 @@ jobs:
 
     - name: 'run HTTP server and call REST API'
       run: |
-        python -m tests.api.server
+        python -m src.api.controller
         sleep 2
-        curl -X POST -i localhost:9999/api/conversations -d '{ "prompt": "describe a random planet in our solar system in 10 words or less" }' || exit 1
+        curl -X POST -i localhost:9998/api/conversations -d '{ "prompt": "describe a random planet in our solar system in 10 words or less" }' -H "Content-Type: application/json" || exit 1
         echo
         
         garak -v \
diff --git a/.gitignore b/.gitignore
index 6c65f4fce..388b28f50 100644
--- a/.gitignore
+++ b/.gitignore
@@ -175,13 +175,13 @@ cython_debug/
 
 # HuggingFace / Microsoft LLM supporting files
 # (these are downloaded for local development via bash script, or inside GH Action workflow context)
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/config.json
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/configuration_phi3.py
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/genai_config.json
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-4k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-4k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx.data
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.json
-tests/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.model
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/config.json
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/configuration_phi3.py
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/genai_config.json
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-4k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi3-mini-4k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx.data
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.json
+src/llm/cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.model
diff --git a/tests/__init__.py b/src/__init__.py
similarity index 100%
rename from tests/__init__.py
rename to src/__init__.py
diff --git a/tests/api/__init__.py b/src/api/__init__.py
similarity index 100%
rename from tests/api/__init__.py
rename to src/api/__init__.py
diff --git a/tests/api/controller.py b/src/api/controller.backup.py
similarity index 98%
rename from tests/api/controller.py
rename to src/api/controller.backup.py
index 10d176e5c..c67d16c9f 100644
--- a/tests/api/controller.py
+++ b/src/api/controller.backup.py
@@ -1,8 +1,8 @@
 import json
 import traceback
 
-from tests.llm.llm import Phi3LanguageModel
-from tests.llm.llm_rag import Phi3LanguageModelWithRag
+from src.llm.llm import Phi3LanguageModel
+from src.llm.llm_rag import Phi3LanguageModelWithRag
 
 class ApiController:
     def __init__(self):
diff --git a/src/api/controller.py b/src/api/controller.py
new file mode 100644
index 000000000..92091f8e7
--- /dev/null
+++ b/src/api/controller.py
@@ -0,0 +1,19 @@
+import logging
+from flask import Flask, jsonify, request
+from src.llm.llm import Phi3LanguageModel
+from src.llm.llm_rag import Phi3LanguageModelWithRag
+
+app = Flask(__name__)
+
+@app.route('/api/conversations', methods=['POST'])
+def get_llm_response():
+    prompt = request.json['prompt']
+    service = Phi3LanguageModel()
+    response = service.invoke(user_input=prompt)
+    return jsonify({'response': response}), 201
+
+if __name__ == '__main__':
+    logger = logging.Logger(name='Flask API', level=logging.DEBUG)
+    print('test')
+    logger.debug('running...')
+    app.run(debug=True, port=9998)
\ No newline at end of file
diff --git a/tests/api/server.py b/src/api/server.py
similarity index 100%
rename from tests/api/server.py
rename to src/api/server.py
diff --git a/tests/llm/__init__.py b/src/llm/__init__.py
similarity index 100%
rename from tests/llm/__init__.py
rename to src/llm/__init__.py
diff --git a/tests/llm/embedding_model.py b/src/llm/embedding_model.py
similarity index 100%
rename from tests/llm/embedding_model.py
rename to src/llm/embedding_model.py
diff --git a/tests/llm/llm.py b/src/llm/llm.py
similarity index 98%
rename from tests/llm/llm.py
rename to src/llm/llm.py
index a07722d5b..0bdf80781 100644
--- a/tests/llm/llm.py
+++ b/src/llm/llm.py
@@ -32,7 +32,7 @@ class Phi3LanguageModel:
         return text
 
 
-    def invoke(self, user_input):
+    def invoke(self, user_input: str) -> str:
         # Set up paths to the local model
         base_dir = os.path.dirname(os.path.abspath(__file__))
         model_path = os.path.join(base_dir, "cpu_and_mobile", "cpu-int4-rtn-block-32-acc-level-4")
diff --git a/tests/llm/llm_rag.py b/src/llm/llm_rag.py
similarity index 100%
rename from tests/llm/llm_rag.py
rename to src/llm/llm_rag.py
diff --git a/tests/llm/phi3-qa.py b/src/llm/phi3-qa.py
similarity index 100%
rename from tests/llm/phi3-qa.py
rename to src/llm/phi3-qa.py
diff --git a/tests/llm/phi3_language_model.py b/src/llm/phi3_language_model.py
similarity index 100%
rename from tests/llm/phi3_language_model.py
rename to src/llm/phi3_language_model.py
diff --git a/tests/llm/rag.py b/src/llm/rag.py
similarity index 100%
rename from tests/llm/rag.py
rename to src/llm/rag.py
diff --git a/tests/tools/garak.config.test.yml b/src/tools/garak.config.test.yml
similarity index 100%
rename from tests/tools/garak.config.test.yml
rename to src/tools/garak.config.test.yml
diff --git a/tests/tools/garak.config.yml b/src/tools/garak.config.yml
similarity index 100%
rename from tests/tools/garak.config.yml
rename to src/tools/garak.config.yml
diff --git a/tests/tools/garak.rest.llm-rag.json b/src/tools/garak.rest.llm-rag.json
similarity index 100%
rename from tests/tools/garak.rest.llm-rag.json
rename to src/tools/garak.rest.llm-rag.json
diff --git a/tests/tools/garak.rest.llm.json b/src/tools/garak.rest.llm.json
similarity index 100%
rename from tests/tools/garak.rest.llm.json
rename to src/tools/garak.rest.llm.json
diff --git a/tests/test.http_api.py b/tests/test.http_api.py
new file mode 100644
index 000000000..e69de29bb