perf: bill

client/data/ChatModels.json

@@ -0,0 +1,26 @@
+{
+  "Gpt35-4k": {
+    "model": "gpt-3.5-turbo",
+    "name": "Gpt35-4k",
+    "contextMaxToken": 4000,
+    "systemMaxToken": 2400,
+    "maxTemperature": 1.2,
+    "price": 1.5
+  },
+  "Gpt35-16k": {
+    "model": "gpt-3.5-turbo-16k",
+    "name": "Gpt35-16k",
+    "contextMaxToken": 16000,
+    "systemMaxToken": 8000,
+    "maxTemperature": 1.2,
+    "price": 3
+  },
+  "Gpt4": {
+    "model": "gpt-4",
+    "name": "Gpt4",
+    "contextMaxToken": 8000,
+    "systemMaxToken": 4000,
+    "maxTemperature": 1.2,
+    "price": 45
+  }
+}

client/data/QAModels.json

@@ -0,0 +1,8 @@
+{
+  "Gpt35-16k": {
+    "model": "gpt-3.5-turbo-16k",
+    "name": "Gpt35-16k",
+    "maxToken": 16000,
+    "price": 3
+  }
+}

client/data/SystemParams.json

@@ -0,0 +1,6 @@
+{
+  "vectorMaxProcess": 10,
+  "qaMaxProcess": 10,
+  "pgIvfflatProbe": 10,
+  "sensitiveCheck": false
+}

client/data/VectorModels.json

@@ -0,0 +1,7 @@
+{
+  "text-embedding-ada-002": {
+    "model": "text-embedding-ada-002",
+    "name": "Embedding-2",
+    "price": 0.2
+  }
+}