added env vars & test cases for HF TGI

.env.example

@@ -2,14 +2,16 @@
 # LLM_MODEL_TYPE=gpt4all-j
 # LLM_MODEL_TYPE=gpt4all
 # LLM_MODEL_TYPE=llamacpp
-LLM_MODEL_TYPE=huggingface
+# LLM_MODEL_TYPE=huggingface
 # LLM_MODEL_TYPE=mosaicml
 # LLM_MODEL_TYPE=stablelm
 # LLM_MODEL_TYPE=openllm
-# LLM_MODEL_TYPE=hftgi
+LLM_MODEL_TYPE=hftgi
 
 OPENLLM_SERVER_URL=http://localhost:64300
 
+HFTGI_SERVER_URL=https://cc93-202-161-34-104.ngrok-free.app
+
 OPENAI_API_KEY=
 
 # if unset, default to "gpt-3.5-turbo"

test.py

@@ -51,6 +51,9 @@ class TestLLMLoader(unittest.TestCase):
     def test_huggingface(self):
         self.run_test_case("huggingface", self.question)
 
+    def test_hftgi(self):
+        self.run_test_case("hftgi", self.question)
+
 
 class TestChatChain(unittest.TestCase):
     question = os.environ.get("CHAT_QUESTION")
@@ -95,6 +98,9 @@ class TestChatChain(unittest.TestCase):
     def test_huggingface(self):
         self.run_test_case("huggingface", self.question)
 
+    def test_hftgi(self):
+        self.run_test_case("hftgi", self.question)
+
 
 class TestQAChain(unittest.TestCase):
     qa_chain: any
@@ -134,6 +140,9 @@ class TestQAChain(unittest.TestCase):
     def test_huggingface(self):
         self.run_test_case("huggingface", self.question)
 
+    def test_hftgi(self):
+        self.run_test_case("hftgi", self.question)
+
 
 def chat():
     start = timer()