Version update for adapters, sdk and llama-index for safety_settings …

…for Vertex (#408)

* Version update for adapters to 0.19.0, sdk to 0.32.0 and llama-index to 0.10.38 for safety_support

* Rol version on tool properties

* Add comment

* Add a comment

backend/adapter_processor/models.py

@@ -1,4 +1,5 @@
 import json
+import logging
 import uuid
 from typing import Any
 
@@ -9,13 +10,15 @@
 from django.db.models import QuerySet
 from unstract.adapters.adapterkit import Adapterkit
 from unstract.adapters.enums import AdapterTypes
-from unstract.adapters.llm.llm_adapter import LLMAdapter
+from unstract.adapters.exceptions import AdapterError
 from utils.models.base_model import BaseModel
 
 ADAPTER_NAME_SIZE = 128
 VERSION_NAME_SIZE = 64
 ADAPTER_ID_LENGTH = 128
 
+logger = logging.getLogger(__name__)
+
 
 class AdapterInstanceModelManager(models.Manager):
     def get_queryset(self) -> QuerySet[Any]:
@@ -146,9 +149,11 @@ def get_context_window_size(self) -> int:
         adapter_metadata = self.get_adapter_meta_data()
         # Get the adapter_instance
         adapter_class = Adapterkit().get_adapter_class_by_adapter_id(self.adapter_id)
-        adapter_instance = adapter_class(adapter_metadata)
-        if isinstance(adapter_instance, LLMAdapter):
+        try:
+            adapter_instance = adapter_class(adapter_metadata)
             return adapter_instance.get_context_window_size()
+        except AdapterError as e:
+            logger.warning(f"Unable to retrieve context window size - {e}")
         return 0
 
 

backend/adapter_processor/serializers.py

@@ -9,6 +9,7 @@
 from rest_framework import serializers
 from rest_framework.serializers import ModelSerializer
 from unstract.adapters.constants import Common as common
+from unstract.adapters.enums import AdapterTypes
 
 from backend.constants import FieldLengthConstants as FLC
 from backend.serializers import AuditSerializer
@@ -63,9 +64,12 @@ def to_representation(self, instance: AdapterInstance) -> dict[str, str]:
 
         adapter_metadata = instance.get_adapter_meta_data()
         rep[AdapterKeys.ADAPTER_METADATA] = adapter_metadata
-        adapter_metadata[AdapterKeys.ADAPTER_CONTEXT_WINDOW_SIZE] = (
-            instance.get_context_window_size()
-        )
+        # Retrieve context window if adapter is a LLM
+        # For other adapter types, context_window is not relevant.
+        if instance.adapter_type == AdapterTypes.LLM.value:
+            adapter_metadata[AdapterKeys.ADAPTER_CONTEXT_WINDOW_SIZE] = (
+                instance.get_context_window_size()
+            )
 
         rep[common.ICON] = AdapterProcessor.get_adapter_data_with_key(
             instance.adapter_id, common.ICON

backend/pyproject.toml

@@ -31,8 +31,8 @@ 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~=0.31.1",
-    "unstract-adapters~=0.18.0",
+    "unstract-sdk~=0.32.0",
+    "unstract-adapters~=0.19.0",
     # ! 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:0.0.24"
+STRUCTURE_TOOL_IMAGE_URL="docker:unstract/tool-structure:0.0.25"
 STRUCTURE_TOOL_IMAGE_NAME="unstract/tool-structure"
-STRUCTURE_TOOL_IMAGE_TAG="0.0.24"
+STRUCTURE_TOOL_IMAGE_TAG="0.0.25"
 
 # Feature Flags
 EVALUATION_SERVER_IP=localhost

prompt-service/pyproject.toml

@@ -13,9 +13,10 @@ dependencies = [
     "peewee~=3.16",
     "nltk~=3.8",
     "flask~=3.0",
-    "llama-index==0.10.28",
+    "llama-index==0.10.38",
     "python-dotenv==1.0.0",
-    "unstract-sdk~=0.31.1",
+    "unstract-sdk~=0.32.0",
+    "unstract-adapters~=0.19.0",
     "redis>=5.0.3",
     "unstract-core @ file:///${PROJECT_ROOT}/../unstract/core",
 ]

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

@@ -517,7 +517,8 @@ def prompt_processor() -> Any:
                                 f"JSON format error : {answer}", LogLevel.ERROR
                             )
                             app.logger.info(
-                                f"Error parsing response (to json): {e}", LogLevel.ERROR
+                                f"Error parsing response (to json): {e}",
+                                LogLevel.ERROR,
                             )
                             structured_output[output[PSKeys.NAME]] = {}
 
@@ -749,10 +750,12 @@ def _retrieve_context(output, doc_id, vector_index, answer) -> str:
     nodes = retriever.retrieve(answer)
     text = ""
     for node in nodes:
-        if node.score > 0.6:
+        # ToDo: May have to fine-tune this value for node score or keep it
+        # configurable at the adapter level
+        if node.score > 0:
             text += node.get_content() + "\n"
         else:
-            app.logger.info("Node score is less than 0.6. " f"Ignored: {node.score}")
+            app.logger.info("Node score is less than 0. " f"Ignored: {node.score}")
     return text
 
 

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~=0.31.1",
-    "unstract-adapters~=0.18.0",
+    "unstract-sdk~=0.32.0",
+    "unstract-adapters~=0.19.0",
     "-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~=0.31.1
+unstract-sdk~=0.32.0

tools/classifier/src/config/properties.json

@@ -2,7 +2,7 @@
   "schemaVersion": "0.0.1",
   "displayName": "File Classifier",
   "functionName": "classify",
-  "toolVersion": "0.0.20",
+  "toolVersion": "0.0.21",
   "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~=0.31.1
+unstract-sdk~=0.32.0

tools/structure/src/config/properties.json

@@ -2,7 +2,7 @@
   "schemaVersion": "0.0.1",
   "displayName": "Structure Tool",
   "functionName": "structure_tool",
-  "toolVersion": "0.0.24",
+  "toolVersion": "0.0.25",
   "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~=0.31.1
+unstract-sdk~=0.32.0

tools/text_extractor/src/config/properties.json

@@ -2,7 +2,7 @@
   "schemaVersion": "0.0.1",
   "displayName": "Text Extractor",
   "functionName": "text_extractor",
-  "toolVersion": "0.0.19",
+  "toolVersion": "0.0.20",
   "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/core/pyproject.toml

@@ -12,7 +12,7 @@ authors = [
 dependencies = [
     "boto3~=1.28.17",
     "botocore~=1.31.17",
-    "llama-index==0.10.28",
+    "llama-index==0.10.38",
     "llama-index-llms-azure-openai==0.1.5",
     "redis~=5.0.1",
     "requests==2.31.0",

unstract/tool-registry/pyproject.toml

@@ -13,7 +13,7 @@ dependencies = [
     "docker~=6.1.3",
     "jsonschema~=4.18.2",
     "PyYAML~=6.0.1",
-    "unstract-adapters~=0.18.0",
+    "unstract-adapters~=0.19.0",
     # ! 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": "0.0.20",
+            "toolVersion": "0.0.21",
             "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:0.0.20",
+        "image_url": "docker:unstract/tool-classifier:0.0.21",
         "image_name": "unstract/tool-classifier",
-        "image_tag": "0.0.20"
+        "image_tag": "0.0.21"
     },
     "text_extractor": {
         "tool_uid": "text_extractor",
         "properties": {
             "schemaVersion": "0.0.1",
             "displayName": "Text Extractor",
             "functionName": "text_extractor",
-            "toolVersion": "0.0.19",
+            "toolVersion": "0.0.20",
             "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:0.0.19",
+        "image_url": "docker:unstract/tool-text-extractor:0.0.20",
         "image_name": "unstract/tool-text-extractor",
-        "image_tag": "0.0.19"
+        "image_tag": "0.0.20"
     }
 }