GPT4o, fix UM GPT sunset

api_cost/api_cost.yaml

@@ -10,6 +10,12 @@ GPT_4:
 # GPT_4_TURBO: ###############
 #   in: 0.01
 #   out: 0.03
+GPT_4o_2024_05_13:
+  in: 0.005
+  out: 0.015
+GPT_4_TURBO_2024_04_09:
+  in: 0.01
+  out: 0.03
 GPT_4_TURBO_0125:
   in: 0.01
   out: 0.03
@@ -93,5 +99,8 @@ LOCAL_MISTRAL_7B_INSTRUCT_V02:
   in: 0.0
   out: 0.0
 LOCAL_CPU_MISTRAL_7B_INSTRUCT_V02_GGUF:
+  in: 0.0
+  out: 0.0
+phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05:
   in: 0.0
   out: 0.0

app.py

@@ -1730,7 +1730,7 @@ Based on preliminary results, the following models perform the best. We are curr
 - `LOCAL Mixtral 7Bx8 Instruct`
 - `LOCAL Mixtral 7B Instruct`
 
-Larger models (e.g., `GPT 4`, `GPT 4 32k`, `Gemini Pro`) do not necessarily perform better for these tasks. MistralAI models exceeded our expectations and perform extremely well. PaLM 2 text-bison@001 also seems to consistently out-perform Gemini Pro.
+Larger models (e.g., `GPT 4`, `Gemini Pro`) do not necessarily perform better for these tasks. MistralAI models exceeded our expectations and perform extremely well. PaLM 2 text-bison@001 also seems to consistently out-perform Gemini Pro.
                     
 The `SLTPvA_short.yaml` prompt also seems to work better with smaller LLMs (e.g., Mistral Tiny). Alternatively, enable double OCR to help the LLM focus on the OCR text given a longer prompt.
                     

vouchervision/VoucherVision_Config_Builder.py

@@ -49,7 +49,7 @@ def build_VV_config(loaded_cfg=None):
 
         check_for_illegal_filenames = False
 
-        LLM_version_user = 'Azure GPT 3.5 Turbo' #'Azure GPT 4 Turbo 1106-preview'
+        LLM_version_user = 'Azure GPT 4' #'Azure GPT 4 Turbo 1106-preview'
         prompt_version = 'SLTPvA_long.yaml' # from ["Version 1", "Version 1 No Domain Knowledge", "Version 2"]
         use_LeafMachine2_collage_images = True # Use LeafMachine2 collage images
         do_create_OCR_helper_image = True

vouchervision/model_maps.py

@@ -3,6 +3,8 @@ class ModelMaps:
     COLORS_EXPENSE_REPORT = {
         'GPT_4': '#32CD32',  # Lime Green
         'GPT_3_5': '#008000',  # Green
+        'GPT_4_TURBO_2024_04_09': '#32CD32',  # Lime Green
+        'GPT_4o_2024_05_13': '#3CB371',  # Lime Green gpt-4o-2024-05-13
         'GPT_3_5_INSTRUCT': '#3CB371',  # Medium Sea Green
         'GPT_4_TURBO_1106': '#228B22',  # Forest Green
         'GPT_4_TURBO_0125': '#228B22',  # Forest Green
@@ -14,11 +16,11 @@ class ModelMaps:
         'GEMINI_PRO': '#1E00FF',  # 
 
         'AZURE_GPT_4': '#800080',  # Purple
-        'AZURE_GPT_4_TURBO_1106': '#9370DB',  # Medium Purple
-        'AZURE_GPT_4_TURBO_0125': '#9370DB',  # Medium Purple
-        'AZURE_GPT_4_32K': '#8A2BE2',  # Blue Violet
-        'AZURE_GPT_3_5_INSTRUCT': '#9400D3',  # Dark Violet
-        'AZURE_GPT_3_5': '#9932CC',  # Dark Orchid
+        # 'AZURE_GPT_4_TURBO_1106': '#9370DB',  # Medium Purple
+        # 'AZURE_GPT_4_TURBO_0125': '#9370DB',  # Medium Purple
+        # 'AZURE_GPT_4_32K': '#8A2BE2',  # Blue Violet
+        # 'AZURE_GPT_3_5_INSTRUCT': '#9400D3',  # Dark Violet
+        # 'AZURE_GPT_3_5': '#9932CC',  # Dark Orchid
 
         'OPEN_MISTRAL_7B': '#FFA07A',  # Light Salmon
         'OPEN_MIXTRAL_8X7B': '#FF8C00',  # Dark Orange
@@ -30,21 +32,26 @@ class ModelMaps:
         'LOCAL_MISTRAL_7B_INSTRUCT_V02': '#4a4a4a',  # Gray
 
         'LOCAL_CPU_MISTRAL_7B_INSTRUCT_V02_GGUF': '#bababa',  # Gray
+
+        'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05': '#bababa',  # Gray
     }
 
     MODELS_OPENAI = ["GPT 4",
                      "GPT 4 32k",
+                     "GPT 4o 2024-05-13", #GPT_4o_2024_05_13
+                     "GPT 4 Turbo 2024-04-09",#GPT_4_TURBO_2024_04_09
                      "GPT 4 Turbo 0125-preview",
                      "GPT 4 Turbo 1106-preview",
                      "GPT 3.5 Turbo",
                      "GPT 3.5 Instruct",
 
                      "Azure GPT 4",
-                     "Azure GPT 4 32k",
-                     "Azure GPT 4 Turbo 0125-preview",
-                     "Azure GPT 4 Turbo 1106-preview",
-                     "Azure GPT 3.5 Turbo",
-                     "Azure GPT 3.5 Instruct",]
+                    #  "Azure GPT 4 32k",
+                    #  "Azure GPT 4 Turbo 0125-preview",
+                    #  "Azure GPT 4 Turbo 1106-preview",
+                    #  "Azure GPT 3.5 Turbo",
+                    #  "Azure GPT 3.5 Instruct",
+                     ]
     
     MODELS_GOOGLE = ["PaLM 2 text-bison@001",
                      "PaLM 2 text-bison@002",
@@ -60,24 +67,27 @@ class ModelMaps:
 
     MODELS_LOCAL = ["LOCAL Mixtral 8x7B Instruct v0.1",
                     "LOCAL Mistral 7B Instruct v0.2",
-                    "LOCAL CPU Mistral 7B Instruct v0.2 GGUF",]
+                    "LOCAL CPU Mistral 7B Instruct v0.2 GGUF",
+                    'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05']
 
-    MODELS_GUI_DEFAULT = "Azure GPT 3.5 Turbo" # "GPT 4 Turbo 1106-preview"
+    MODELS_GUI_DEFAULT = "Azure GPT 4" # "GPT 4 Turbo 1106-preview"
 
     version_mapping_cost = {
         'GPT 4 32k': 'GPT_4_32K',
         'GPT 4': 'GPT_4',
+        "GPT 4o 2024-05-13": 'GPT_4o_2024_05_13',
+        "GPT 4 Turbo 2024-04-09": 'GPT_4_TURBO_2024_04_09',
         'GPT 4 Turbo 0125-preview': 'GPT_4_TURBO_0125',
         'GPT 4 Turbo 1106-preview': 'GPT_4_TURBO_1106',
         'GPT 3.5 Instruct': 'GPT_3_5_INSTRUCT',
         'GPT 3.5 Turbo': 'GPT_3_5',
 
-        'Azure GPT 4 32k': 'AZURE_GPT_4_32K',
+        # 'Azure GPT 4 32k': 'AZURE_GPT_4_32K',
         'Azure GPT 4': 'AZURE_GPT_4',
-        'Azure GPT 4 Turbo 0125-preview': 'AZURE_GPT_4_TURBO_0125',
-        'Azure GPT 4 Turbo 1106-preview': 'AZURE_GPT_4_TURBO_1106',
-        'Azure GPT 3.5 Instruct': 'AZURE_GPT_3_5_INSTRUCT',
-        'Azure GPT 3.5 Turbo': 'AZURE_GPT_3_5',
+        # 'Azure GPT 4 Turbo 0125-preview': 'AZURE_GPT_4_TURBO_0125',
+        # 'Azure GPT 4 Turbo 1106-preview': 'AZURE_GPT_4_TURBO_1106',
+        # 'Azure GPT 3.5 Instruct': 'AZURE_GPT_3_5_INSTRUCT',
+        # 'Azure GPT 3.5 Turbo': 'AZURE_GPT_3_5',
 
         'Gemini Pro': 'GEMINI_PRO',
         'PaLM 2 text-unicorn@001': 'PALM2_TU_1',
@@ -94,25 +104,29 @@ class ModelMaps:
         'LOCAL Mistral 7B Instruct v0.2': 'LOCAL_MISTRAL_7B_INSTRUCT_V02',
 
         'LOCAL CPU Mistral 7B Instruct v0.2 GGUF': 'LOCAL_CPU_MISTRAL_7B_INSTRUCT_V02_GGUF',
+
+        'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05': 'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05',
     }
 
     @classmethod
     def get_version_has_key(cls, key, has_key_openai, has_key_azure_openai, has_key_google_application_credentials, has_key_mistral):
         # Define the mapping for 'has_key' values
         version_has_key = {
+            "GPT 4 Turbo 2024-04-09": has_key_openai,
             'GPT 4 Turbo 1106-preview': has_key_openai,
             'GPT 4 Turbo 0125-preview': has_key_openai,
             'GPT 4':  has_key_openai,
+            "GPT 4o 2024-05-13": has_key_openai, 
             'GPT 4 32k':  has_key_openai,
             'GPT 3.5 Turbo':  has_key_openai,
             'GPT 3.5 Instruct':  has_key_openai,
 
-            'Azure GPT 3.5 Turbo': has_key_azure_openai,
-            'Azure GPT 3.5 Instruct': has_key_azure_openai,
+            # 'Azure GPT 3.5 Turbo': has_key_azure_openai,
+            # 'Azure GPT 3.5 Instruct': has_key_azure_openai,
             'Azure GPT 4': has_key_azure_openai,
-            'Azure GPT 4 Turbo 1106-preview': has_key_azure_openai,
-            'Azure GPT 4 Turbo 0125-preview': has_key_azure_openai,
-            'Azure GPT 4 32k': has_key_azure_openai,
+            # 'Azure GPT 4 Turbo 1106-preview': has_key_azure_openai,
+            # 'Azure GPT 4 Turbo 0125-preview': has_key_azure_openai,
+            # 'Azure GPT 4 32k': has_key_azure_openai,
 
             'PaLM 2 text-bison@001':  has_key_google_application_credentials,
             'PaLM 2 text-bison@002':  has_key_google_application_credentials,
@@ -129,12 +143,16 @@ class ModelMaps:
             'LOCAL Mistral 7B Instruct v0.2':  True,
 
             'LOCAL CPU Mistral 7B Instruct v0.2 GGUF':  True,
+
+            'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05': True
         }
         return version_has_key.get(key)
 
     @classmethod
     def get_version_mapping_is_azure(cls, key):
         version_mapping_is_azure = {
+            "GPT 4o 2024-05-13": False, 
+            "GPT 4 Turbo 2024-04-09": False,
             "GPT 4 Turbo 1106-preview": False,
             "GPT 4 Turbo 0125-preview": False,
             'GPT 4': False,
@@ -142,12 +160,12 @@ class ModelMaps:
             'GPT 3.5 Turbo':  False,
             'GPT 3.5 Instruct':  False,
 
-            'Azure GPT 3.5 Turbo': True,
-            'Azure GPT 3.5 Instruct': True,
+            # 'Azure GPT 3.5 Turbo': True,
+            # 'Azure GPT 3.5 Instruct': True,
             'Azure GPT 4': True,
-            'Azure GPT 4 Turbo 1106-preview': True,
-            'Azure GPT 4 Turbo 0125-preview': True,
-            'Azure GPT 4 32k': True,
+            # 'Azure GPT 4 Turbo 1106-preview': True,
+            # 'Azure GPT 4 Turbo 0125-preview': True,
+            # 'Azure GPT 4 32k': True,
 
             'PaLM 2 text-bison@001':  False,
             'PaLM 2 text-bison@002':  False,
@@ -164,6 +182,8 @@ class ModelMaps:
             'LOCAL Mistral 7B Instruct v0.2':  False,
 
             'LOCAL CPU Mistral 7B Instruct v0.2 GGUF':  False,
+
+            'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05': False
         }
         return version_mapping_is_azure.get(key)
 
@@ -182,7 +202,13 @@ class ModelMaps:
 
         elif key == 'GPT_4_32K':
             return 'gpt-4-32k'
+
+        elif key == 'GPT_4o_2024_05_13':
+            return 'gpt-4o-2024-05-13'
         
+        elif key == 'GPT_4_TURBO_2024_04_09':
+            return 'gpt-4-turbo-2024-04-09'
+
         elif key == 'GPT_4_TURBO_1106':
             return 'gpt-4-1106-preview'
         
@@ -190,23 +216,23 @@ class ModelMaps:
             return 'gpt-4-0125-preview'
         
         ### Azure
-        elif key == 'AZURE_GPT_3_5':
-            return 'gpt-35-turbo-0125'
+        # elif key == 'AZURE_GPT_3_5':
+        #     return 'gpt-35-turbo-0125'
 
-        elif key == 'AZURE_GPT_3_5_INSTRUCT':
-            return 'gpt-35-turbo-instruct'
+        # elif key == 'AZURE_GPT_3_5_INSTRUCT':
+        #     return 'gpt-35-turbo-instruct'
         
         elif key == 'AZURE_GPT_4':
             return "gpt-4"
     
-        elif key == 'AZURE_GPT_4_TURBO_1106':
-            return "gpt-4-1106-preview"
+        # elif key == 'AZURE_GPT_4_TURBO_1106':
+        #     return "gpt-4-1106-preview"
         
-        elif key == 'AZURE_GPT_4_TURBO_0125':
-            return 'gpt-4-0125-preview'
+        # elif key == 'AZURE_GPT_4_TURBO_0125':
+        #     return 'gpt-4-0125-preview'
         
-        elif key == 'AZURE_GPT_4_32K':
-            return "gpt-4-32k"
+        # elif key == 'AZURE_GPT_4_32K':
+        #     return "gpt-4-32k"
         
         ### Google
         elif key == 'PALM2_TB_1':
@@ -248,6 +274,14 @@ class ModelMaps:
         ### Mistral LOCAL CPU
         elif key == 'LOCAL_CPU_MISTRAL_7B_INSTRUCT_V02_GGUF':
             return 'Mistral-7B-Instruct-v0.2-GGUF'
+        
+
+
+        ### LOCAL custom fine-tuned
+        elif key == 'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05':
+            return 'phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05'
+        
+
 
         else:
             raise ValueError(f"Invalid model name {key}. See model_maps.py")