fix: Enhance classifier prompt to avoid explanation (#511)

* Enhance classifier prompt to avoid explanation

* Bumped classifier in tool registry

Author: chandrasekharan-zipstack

backend/adapter_processor/constants.py

@@ -21,8 +21,8 @@ class AdapterKeys:
     X2TEXT_DEFAULT = "x2text_default"
     SHARED_USERS = "shared_users"
     ADAPTER_NAME_EXISTS = (
-        "Configuration with this Name already exists. "
-        "Please try with a different Name"
+        "Configuration with this name already exists within your organisation. "
+        "Please try with a different name."
     )
     ADAPTER_CREATED_BY = "created_by_email"
     ADAPTER_CONTEXT_WINDOW_SIZE = "context_window_size"

backend/adapter_processor_v2/constants.py

@@ -21,8 +21,8 @@ class AdapterKeys:
     X2TEXT_DEFAULT = "x2text_default"
     SHARED_USERS = "shared_users"
     ADAPTER_NAME_EXISTS = (
-        "Configuration with this Name already exists. "
-        "Please try with a different Name"
+        "Configuration with this name already exists within your organisation. "
+        "Please try with a different name"
     )
     ADAPTER_CREATED_BY = "created_by_email"
     ADAPTER_CONTEXT_WINDOW_SIZE = "context_window_size"

tools/classifier/sample.env

@@ -1,11 +1,7 @@
-PLATFORM_SERVICE_HOST=
-PLATFORM_SERVICE_PORT=
-PLATFORM_SERVICE_API_KEY=
-TOOL_DATA_DIR=
+PLATFORM_SERVICE_HOST=http://unstract-platform-service
+PLATFORM_SERVICE_PORT=3001
+PLATFORM_SERVICE_API_KEY=<add_platform_key_from_Unstract_frontend>
+TOOL_DATA_DIR=../data_dir
 
-# Azure OpenAI
-OPENAI_API_KEY=
-OPENAI_API_BASE=
-OPENAI_API_VERSION=
-OPENAI_API_ENGINE=
-OPENAI_API_MODEL=
+X2TEXT_HOST=http://unstract-x2text-service
+X2TEXT_PORT=3004

tools/classifier/src/config/properties.json

@@ -2,7 +2,7 @@
   "schemaVersion": "0.0.1",
   "displayName": "File Classifier",
   "functionName": "classify",
-  "toolVersion": "0.0.26",
+  "toolVersion": "0.0.27",
   "description": "Classifies a file into a bin based on its contents",
   "input": {
     "description": "File to be classified"

tools/classifier/src/main.py

@@ -27,7 +27,9 @@ def validate(self, input_file: str, settings: dict[str, Any]) -> None:
         if not llm_adapter_instance_id:
             self.stream_error_and_exit("Choose an LLM to process the classifier")
         if not text_extraction_adapter_id:
-            self.stream_error_and_exit("Choose an LLM to extract the documents")
+            self.stream_error_and_exit(
+                "Choose a text extractor to extract the documents"
+            )
 
     def run(
         self,
@@ -99,9 +101,10 @@ def run(
 
         prompt = (
             f"Classify the following text into one of the following categories: {' '.join(bins_with_quotes)}.\n\n"  # noqa: E501
-            f"Your categorization should be strictly exactly one of the items in the "  # noqa: E501
-            f"categories given. Find a semantic match of category if possible. If it does not categorize well "  # noqa: E501
-            f"into any of the listed categories, categorize it as 'unknown'.\n\nText:\n\n{text}\n\n\nCategory:"  # noqa: E501
+            "Your categorization should be strictly exactly one of the items in the "  # noqa: E501
+            "categories given, do not provide any explanation. Find a semantic match of category if possible. "  # noqa: E501
+            "If it does not categorize well into any of the listed categories, categorize it as 'unknown'.\n\n"  # noqa: E501
+            f"Text:\n\n{text}\n\n\nCategory:"
         )
 
         settings_string = "".join(str(value) for value in settings.values())

unstract/tool-registry/src/unstract/tool_registry/public_tools.json

@@ -5,7 +5,7 @@
             "schemaVersion": "0.0.1",
             "displayName": "File Classifier",
             "functionName": "classify",
-            "toolVersion": "0.0.26",
+            "toolVersion": "0.0.27",
             "description": "Classifies a file into a bin based on its contents",
             "input": {
                 "description": "File to be classified"
@@ -139,9 +139,9 @@
             }
         },
         "icon": "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n<svg\n   enable-background=\"new 0 0 20 20\"\n   height=\"48\"\n   viewBox=\"0 0 20 20\"\n   width=\"48\"\n   fill=\"#000000\"\n   version=\"1.1\"\n   id=\"svg8109\"\n   sodipodi:docname=\"folder_copy_black_48dp.svg\"\n   xmlns:inkscape=\"http://www.inkscape.org/namespaces/inkscape\"\n   xmlns:sodipodi=\"http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd\"\n   xmlns=\"http://www.w3.org/2000/svg\"\n   xmlns:svg=\"http://www.w3.org/2000/svg\">\n  <defs\n     id=\"defs8113\" />\n  <sodipodi:namedview\n     id=\"namedview8111\"\n     pagecolor=\"#ffffff\"\n     bordercolor=\"#000000\"\n     borderopacity=\"0.25\"\n     inkscape:showpageshadow=\"2\"\n     inkscape:pageopacity=\"0.0\"\n     inkscape:pagecheckerboard=\"0\"\n     inkscape:deskcolor=\"#d1d1d1\"\n     showgrid=\"false\" />\n  <g\n     id=\"g8099\">\n    <rect\n       fill=\"none\"\n       height=\"20\"\n       width=\"20\"\n       x=\"0\"\n       id=\"rect8097\"\n       y=\"0\" />\n  </g>\n  <g\n     id=\"g8107\"\n     style=\"fill:#ff4d6d;fill-opacity:1\">\n    <g\n       id=\"g8105\"\n       style=\"fill:#ff4d6d;fill-opacity:1\">\n      <path\n         d=\"M 2.5,5 H 1 V 15.5 C 1,16.33 1.67,17 2.5,17 H 15.68 V 15.5 H 2.5 Z\"\n         id=\"path8101\"\n         style=\"fill:#ff4d6d;fill-opacity:1\" />\n      <path\n         d=\"M 16.5,4 H 11 L 9,2 H 5.5 C 4.67,2 4,2.67 4,3.5 v 9 C 4,13.33 4.67,14 5.5,14 h 11 c 0.83,0 1.5,-0.67 1.5,-1.5 v -7 C 18,4.67 17.33,4 16.5,4 Z m 0,8.5 h -11 v -9 h 2.88 l 2,2 h 6.12 z\"\n         id=\"path8103\"\n         style=\"fill:#ff4d6d;fill-opacity:1\" />\n    </g>\n  </g>\n</svg>\n",
-        "image_url": "docker:unstract/tool-classifier:0.0.26",
+        "image_url": "docker:unstract/tool-classifier:0.0.27",
         "image_name": "unstract/tool-classifier",
-        "image_tag": "0.0.26"
+        "image_tag": "0.0.27"
     },
     "text_extractor": {
         "tool_uid": "text_extractor",