feat: Updated SDK and adapters, prompt service error handling improvm…

…ents (#320)

* Updated SDK and adapters, prompt service error handling improvments

* Updated tool registry for SDK 0.25.0

backend/pyproject.toml

@@ -30,8 +30,8 @@ dependencies = [
     "python-socketio==5.9.0", # For log_events
     "social-auth-app-django==5.3.0", # For OAuth
     "social-auth-core==4.4.2", # For OAuth
-    "unstract-sdk~=0.24.0",
-    "unstract-adapters~=0.12.1",
+    "unstract-sdk~=0.25.0",
+    "unstract-adapters~=0.14.0",
     # ! IMPORTANT!
     # Indirect local dependencies usually need to be added in their own projects
     # as: https://pdm-project.org/latest/usage/dependency/#local-dependencies.

backend/sample.env

@@ -89,9 +89,9 @@ PROMPT_PORT=3003
 PROMPT_STUDIO_FILE_PATH=/app/prompt-studio-data
 
 # Structure Tool
-STRUCTURE_TOOL_IMAGE_URL="docker:unstract/tool-structure:0.0.18"
+STRUCTURE_TOOL_IMAGE_URL="docker:unstract/tool-structure:0.0.19"
 STRUCTURE_TOOL_IMAGE_NAME="unstract/tool-structure"
-STRUCTURE_TOOL_IMAGE_TAG="0.0.18"
+STRUCTURE_TOOL_IMAGE_TAG="0.0.19"
 
 # Feature Flags
 EVALUATION_SERVER_IP=localhost

prompt-service/pyproject.toml

@@ -15,7 +15,7 @@ dependencies = [
     "flask~=3.0",
     "llama-index==0.10.28",
     "python-dotenv==1.0.0",
-    "unstract-sdk~=0.24.0",
+    "unstract-sdk~=0.25.0",
     "redis>=5.0.3",
     "unstract-core @ file:///${PROJECT_ROOT}/../unstract/core",
 ]

prompt-service/src/unstract/prompt_service/constants.py

@@ -63,3 +63,4 @@ class RunLevel(Enum):
 
     RUN = "RUN"
     EVAL = "EVAL"
+    CHALLENGE = "CHALLENGE"

prompt-service/src/unstract/prompt_service/exceptions.py

@@ -18,6 +18,7 @@ class ErrorResponse:
 
 class APIError(HTTPException):
     code = 500
+    message = DEFAULT_ERR_MESSAGE
 
     def __init__(
         self,
@@ -42,3 +43,13 @@ def to_dict(self):
 
     def __str__(self):
         return str(self.message)
+
+
+class NoPayloadError(APIError):
+    code = 400
+    message = "Bad Request / No payload"
+
+
+class RateLimitError(APIError):
+    code = 429
+    message = "Running into rate limit errors, please try again later"

prompt-service/src/unstract/prompt_service/main.py

@@ -12,11 +12,17 @@
 from unstract.prompt_service.authentication_middleware import AuthenticationMiddleware
 from unstract.prompt_service.constants import PromptServiceContants as PSKeys
 from unstract.prompt_service.constants import RunLevel
-from unstract.prompt_service.exceptions import APIError, ErrorResponse
+from unstract.prompt_service.exceptions import (
+    APIError,
+    ErrorResponse,
+    NoPayloadError,
+    RateLimitError,
+)
 from unstract.prompt_service.helper import EnvLoader, plugin_loader
 from unstract.prompt_service.prompt_ide_base_tool import PromptServiceBaseTool
 from unstract.sdk.constants import LogLevel
 from unstract.sdk.embedding import ToolEmbedding
+from unstract.sdk.exceptions import RateLimitError as SdkRateLimitError
 from unstract.sdk.exceptions import SdkError
 from unstract.sdk.index import ToolIndex
 from unstract.sdk.llm import ToolLLM
@@ -159,17 +165,15 @@ def wrapper(*args: Any, **kwargs: Any) -> Any:
 @app.route(
     "/answer-prompt",
     endpoint="answer_prompt",
-    methods=["POST", "GET", "DELETE"],
+    methods=["POST"],
 )
 @authentication_middleware
 def prompt_processor() -> Any:
-    result: dict[str, Any] = {}
     platform_key = AuthenticationMiddleware.get_token_from_auth_header(request)
     if request.method == "POST":
         payload: dict[Any, Any] = request.json
         if not payload:
-            result["error"] = "Bad Request / No payload"
-            return result, 400
+            raise NoPayloadError()
     outputs = payload.get(PSKeys.OUTPUTS)
     tool_id: str = payload.get(PSKeys.TOOL_ID, "")
     file_hash = payload.get(PSKeys.FILE_HASH)
@@ -302,6 +306,14 @@ def prompt_processor() -> Any:
                     msg,
                 )
                 raise APIError(message=msg)
+            # TODO: Use vectorDB name when available
+            _publish_log(
+                log_events_id,
+                {"tool_id": tool_id, "prompt_key": prompt_name, "doc_name": doc_name},
+                LogLevel.DEBUG,
+                RunLevel.RUN,
+                "Fetched context from vector DB",
+            )
 
         assertion_failed = False
         answer = "yes"
@@ -522,6 +534,17 @@ def prompt_processor() -> Any:
             challenge_plugin: dict[str, Any] = plugins.get("challenge", {})
             try:
                 if challenge_plugin:
+                    _publish_log(
+                        log_events_id,
+                        {
+                            "tool_id": tool_id,
+                            "prompt_key": prompt_name,
+                            "doc_name": doc_name,
+                        },
+                        LogLevel.INFO,
+                        RunLevel.CHALLENGE,
+                        "Challenging response",
+                    )
                     tool_settings: dict[str, Any] = {
                         PSKeys.PREAMBLE: output[PSKeys.PREAMBLE],
                         PSKeys.POSTAMBLE: output[PSKeys.POSTAMBLE],
@@ -549,6 +572,17 @@ def prompt_processor() -> Any:
                 app.logger.error(
                     "Failed to challenge prompt %s: %s", output["name"], str(e)
                 )
+                _publish_log(
+                    log_events_id,
+                    {
+                        "tool_id": tool_id,
+                        "prompt_key": prompt_name,
+                        "doc_name": doc_name,
+                    },
+                    LogLevel.ERROR,
+                    RunLevel.CHALLENGE,
+                    "Error while challenging response",
+                )
 
         #
         # Evaluate the prompt.
@@ -743,6 +777,8 @@ def run_completion(
         answer: str = completion[PSKeys.RESPONSE].text
         return answer
     # TODO: Catch and handle specific exception here
+    except SdkRateLimitError as e:
+        raise RateLimitError(f"Rate limit error. {str(e)}") from e
     except Exception as e:
         app.logger.info(f"Error fetching response for prompt: {e}.")
         # TODO: Publish this error as a FE update

pyproject.toml

@@ -40,8 +40,8 @@ hook-check-django-migrations = [
     "psycopg2-binary==2.9.9",
     "python-dotenv==1.0.0",
     "python-magic==0.4.27",
-    "unstract-sdk~=0.24.0",
-    "unstract-adapters~=0.12.1",
+    "unstract-sdk~=0.25.0",
+    "unstract-adapters~=0.14.0",
     "-e unstract-connectors @ file:///${PROJECT_ROOT}/unstract/connectors",
     "-e unstract-core @ file:///${PROJECT_ROOT}/unstract/core",
     "-e unstract-flags @ file:///${PROJECT_ROOT}/unstract/flags",

tools/classifier/requirements.txt

@@ -1,4 +1,4 @@
 # Add your dependencies here
 
 # Required for all unstract tools
-unstract-sdk~=0.24.0
+unstract-sdk~=0.25.0

tools/classifier/src/config/properties.json

@@ -2,7 +2,7 @@
   "schemaVersion": "0.0.1",
   "displayName": "File Classifier",
   "functionName": "classify",
-  "toolVersion": "0.0.15",
+  "toolVersion": "0.0.16",
   "description": "Classifies a file into a bin based on its contents",
   "input": {
     "description": "File to be classified"

tools/structure/requirements.txt

@@ -1,4 +1,4 @@
 # Add your dependencies here
 
 # Required for all unstract tools
-unstract-sdk~=0.24.0
+unstract-sdk~=0.25.0

tools/structure/src/config/properties.json

@@ -2,7 +2,7 @@
   "schemaVersion": "0.0.1",
   "displayName": "Structure Tool",
   "functionName": "structure_tool",
-  "toolVersion": "0.0.18",
+  "toolVersion": "0.0.19",
   "description": "This is a template tool which can answer set of input prompts designed in the Prompt Studio",
   "input": {
     "description": "File that needs to be indexed and parsed for answers"

tools/text_extractor/requirements.txt

@@ -1,4 +1,4 @@
 # Add your dependencies here
 
 # Required for all unstract tools
-unstract-sdk~=0.24.0
+unstract-sdk~=0.25.0

tools/text_extractor/src/config/properties.json

@@ -2,7 +2,7 @@
   "schemaVersion": "0.0.1",
   "displayName": "Text Extractor",
   "functionName": "text_extractor",
-  "toolVersion": "0.0.14",
+  "toolVersion": "0.0.15",
   "description": "The Text Extractor is a powerful tool designed to convert documents to its text form or Extract texts from documents",
   "input": {
     "description": "Document"

unstract/tool-registry/pyproject.toml

@@ -13,7 +13,7 @@ dependencies = [
     "docker~=6.1.3",
     "jsonschema~=4.18.2",
     "PyYAML~=6.0.1",
-    "unstract-adapters~=0.12.1",
+    "unstract-adapters~=0.14.0",
     # ! IMPORTANT!
     # Local dependencies usually need to be added as:
     # https://pdm-project.org/latest/usage/dependency/#local-dependencies

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

@@ -5,7 +5,7 @@
             "schemaVersion": "0.0.1",
             "displayName": "File Classifier",
             "functionName": "classify",
-            "toolVersion": "0.0.15",
+            "toolVersion": "0.0.16",
             "description": "Classifies a file into a bin based on its contents",
             "input": {
                 "description": "File to be classified"
@@ -139,17 +139,17 @@
             }
         },
         "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:0.0.15",
+        "image_url": "docker:unstract/tool-classifier:0.0.16",
         "image_name": "unstract/tool-classifier",
-        "image_tag": "0.0.15"
+        "image_tag": "0.0.16"
     },
     "text_extractor": {
         "tool_uid": "text_extractor",
         "properties": {
             "schemaVersion": "0.0.1",
             "displayName": "Text Extractor",
             "functionName": "text_extractor",
-            "toolVersion": "0.0.14",
+            "toolVersion": "0.0.15",
             "description": "The Text Extractor is a powerful tool designed to convert documents to its text form or Extract texts from documents",
             "input": {
                 "description": "Document"
@@ -224,8 +224,8 @@
             }
         },
         "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-text-extractor:0.0.14",
+        "image_url": "docker:unstract/tool-text-extractor:0.0.15",
         "image_name": "unstract/tool-text-extractor",
-        "image_tag": "0.0.14"
+        "image_tag": "0.0.15"
     }
 }