kolzchut-ragbot 1.6.0__tar.gz → 1.6.1__tar.gz

{kolzchut_ragbot-1.6.0 → kolzchut_ragbot-1.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kolzchut-ragbot
-Version: 1.6.0
+Version: 1.6.1
 Summary: A search engine using machine learning models and Elasticsearch for advanced document retrieval.
 Home-page: https://github.com/shmuelrob/rag-bot
 Author: Shmuel Robinov

{kolzchut_ragbot-1.6.0 → kolzchut_ragbot-1.6.1}/kolzchut_ragbot/engine.py

@@ -286,42 +286,6 @@ class Engine:
         full_document = unite_docs_to_single_instance(parts_of_documents)
         return full_document
 
-    def transform_document_to_full_page(self, document: dict) -> dict:
-        """
-        Adds the full page content to the document by retrieving it from Elasticsearch.
-
-        Args:
-            document (dict): The document to which the full page content will be added.
-
-        Returns:
-            dict: The updated document with the full page content added.
-        """
-        if not document.get("page_id"):
-            return document
-        full_document = self.get_full_document_by_page_id(document["page_id"])
-        if full_document and full_document.get("content"):
-            document["content"] = full_document["content"]
-        return document
-
-    def get_full_document_by_page_id(self, page_id: int) -> dict | None:
-        """
-        Retrieves a unified document instance for a given page_id by searching all indices in Elasticsearch.
-
-        Args:
-            page_id (int): The page ID to search for.
-
-        Returns:
-            dict | None: A single dict representing the united document (with metadata and concatenated content),
-                        or None if no documents are found.
-        """
-        es_client = self.elastic_model.es_client
-        indices = es_client.indices.get_alias(index="*").keys()
-        parts_of_documents = find_page_id_in_all_indices(page_id=page_id, es_client=es_client, indices=indices)
-        if not parts_of_documents:
-            return None
-        full_document = unite_docs_to_single_instance(parts_of_documents)
-        return full_document
-
 
 engine = None
 

{kolzchut_ragbot-1.6.0 → kolzchut_ragbot-1.6.1}/kolzchut_ragbot/llm_client.py

@@ -7,5 +7,5 @@ class LLMClient(ABC):
     def __init__(self):
         self.field_for_answer = definitions.field_for_llm
     @abstractmethod
-    def answer(self, _question, _top_k_docs) -> tuple[str, float, int]:
+    def answer(self, _question, _top_k_docs) -> tuple[str, float, int, dict]:
         raise NotImplementedError

{kolzchut_ragbot-1.6.0 → kolzchut_ragbot-1.6.1}/kolzchut_ragbot.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kolzchut-ragbot
-Version: 1.6.0
+Version: 1.6.1
 Summary: A search engine using machine learning models and Elasticsearch for advanced document retrieval.
 Home-page: https://github.com/shmuelrob/rag-bot
 Author: Shmuel Robinov

{kolzchut_ragbot-1.6.0 → kolzchut_ragbot-1.6.1}/pyproject.toml

@@ -14,7 +14,7 @@ push            = false
 
 [tool.poetry]
 name = "ragbot"
-version = "1.6.0"
+version = "1.6.1"
 description = ""
 authors = ["Your Name <your.email@example.com>"]
 

{kolzchut_ragbot-1.6.0 → kolzchut_ragbot-1.6.1}/setup.py

@@ -7,7 +7,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='kolzchut-ragbot',
-    version='1.6.0',
+    version='1.6.1',
     author='Shmuel Robinov',
     author_email='shmuel_robinov@webiks.com',
     description='A search engine using machine learning models and Elasticsearch for advanced document retrieval.',

{kolzchut_ragbot-1.6.0 → kolzchut_ragbot-1.6.1}/test/test_engine.py

@@ -135,8 +135,8 @@ class TestEngine:
                 {'page_id': 5, 'title': 'title5'}
             ], {})
 
-            llm_client.answer.return_value = ('answer', 0.5, 100)
-            actual_top_k_documents, actual_gpt_answer, actual_stats, _ = engine.answer_query("test query", 5, 'gpt-4o')
+            llm_client.answer.return_value = ('answer', 0.5, 100, {})
+            actual_top_k_documents, actual_gpt_answer, actual_stats, all_docs_and_score, request_params = engine.answer_query("test query", 5, 'gpt-4o')
 
             expected_top_k_documents = [
                 {'page_id': 3, 'title': 'title3'},
@@ -156,4 +156,3 @@ class TestEngine:
             assert expected_top_k_documents == actual_top_k_documents
             assert expected_gpt_answer == actual_gpt_answer
             assert expected_stats == actual_stats
-