kolzchut-ragbot 1.4.1__tar.gz → 1.5.0__tar.gz

kolzchut_ragbot-1.5.0/PKG-INFO

@@ -0,0 +1,76 @@
+Metadata-Version: 2.4
+Name: kolzchut-ragbot
+Version: 1.5.0
+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
+Author-email: shmuel_robinov@webiks.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: elasticsearch==8.17.1
+Requires-Dist: sentence-transformers==3.4.1
+Requires-Dist: torch==2.6.0
+Requires-Dist: transformers==4.48.3
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# kolzchut-ragbot
+
+## Overview
+
+This project is a search engine that uses machine learning models and Elasticsearch to provide advanced document retrieval.
+You can use [kolzchut-ragbot](https://github.com/shmuelrob/rag-bot) to demonstrate the engine's document retrieval abilities.
+
+## Features
+
+- Document representation and validation
+- Document embedding and indexing in Elasticsearch
+- Advanced search using machine learning model
+- Integration with LLM (Large Language Model) client for query answering
+
+## Installation
+
+### From PyPI
+
+```bash
+pip install kolzchut-ragbot
+```
+
+### From Source
+
+1. Clone the repository:
+   
+   ```bash
+   git clone https://github.com/shmuelrob/rag-bot.git
+   cd rag-bot
+   ```
+
+2. Create a virtual environment and activate it:  
+
+   ```bash
+   python -m venv venv
+   source venv/bin/activate  # On Windows use: venv\Scripts\activate
+   ```
+
+3. Install the required dependencies:  
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+## Configuration
+
+Set the following environment variables:
+
+- `ES_EMBEDDING_INDEX`: The name of the Elasticsearch index for embeddings.
+- `TOKENIZER_LOCATION`: The location of the tokenizer model.

kolzchut_ragbot-1.5.0/README.md

@@ -0,0 +1,50 @@
+# kolzchut-ragbot
+
+## Overview
+
+This project is a search engine that uses machine learning models and Elasticsearch to provide advanced document retrieval.
+You can use [kolzchut-ragbot](https://github.com/shmuelrob/rag-bot) to demonstrate the engine's document retrieval abilities.
+
+## Features
+
+- Document representation and validation
+- Document embedding and indexing in Elasticsearch
+- Advanced search using machine learning model
+- Integration with LLM (Large Language Model) client for query answering
+
+## Installation
+
+### From PyPI
+
+```bash
+pip install kolzchut-ragbot
+```
+
+### From Source
+
+1. Clone the repository:
+   
+   ```bash
+   git clone https://github.com/shmuelrob/rag-bot.git
+   cd rag-bot
+   ```
+
+2. Create a virtual environment and activate it:  
+
+   ```bash
+   python -m venv venv
+   source venv/bin/activate  # On Windows use: venv\Scripts\activate
+   ```
+
+3. Install the required dependencies:  
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+## Configuration
+
+Set the following environment variables:
+
+- `ES_EMBEDDING_INDEX`: The name of the Elasticsearch index for embeddings.
+- `TOKENIZER_LOCATION`: The location of the tokenizer model.

{kolzchut_ragbot-1.4.1 → kolzchut_ragbot-1.5.0}/kolzchut_ragbot/Document.py

@@ -1,101 +1,101 @@
-import json
-import os
-
-DEFINITIONS_FILE = os.getenv("DOCUMENT_DEFINITION_CONFIG", "example-conf.json")
-
-
-class DocumentFieldDefinition:
-    """
-    Represents the definition of a document field.
-
-    Attributes:
-        field_name (str): The name of the field.
-        required (bool): Indicates if the field is required. Default is False.
-    """
-    def __init__(self, field_name: str, required: bool = False):
-        self.field_name = field_name
-        self.required = required
-
-
-class DocumentDefinitions:
-    """
-    Represents the definitions for a document.
-
-    Attributes:
-        saved_fields (dict[str, DocumentFieldDefinition]): A dictionary of saved fields.
-        models (dict[str, str]): A dictionary of models.
-        identifier (str): The identifier field.
-        field_for_llm (str, optional): The field for LLM. Default is None.
-    """
-    def __init__(self, saved_fields: dict[str, DocumentFieldDefinition], models: dict[str, str],
-                 identifier: str, field_for_llm: str = None):
-        self.saved_fields = saved_fields
-        self.models = models
-        self.identifier = identifier
-        self.field_for_llm = field_for_llm
-
-
-def initialize_definitions():
-    """
-    Initializes the document definitions by reading the configuration file.
-
-    Raises:
-        ValueError: If the identifier field is not one of the saved fields or if any model field is not one of the saved fields.
-
-    Returns:
-        DocumentDefinitions: The initialized document definitions.
-    """
-    with open(DEFINITIONS_FILE, 'r', encoding='utf-8') as f:
-        definitions = json.load(f)
-
-        saved_fields = definitions['saved_fields']
-        models = definitions['models']
-        identifier_field = definitions['identifier_field']
-        field_for_llm = definitions.get('field_for_llm', None)
-        if identifier_field not in saved_fields.keys():
-            raise ValueError("identifier_field must be one of the saved fields, check the configuration file")
-
-        for embedded_field in models.values():
-            if embedded_field not in saved_fields.keys():
-                raise ValueError(f"{embedded_field} must be one of the saved fields {saved_fields.keys()}, check the configuration file")
-
-        return DocumentDefinitions(saved_fields, models, identifier_field, field_for_llm)
-
-
-definitions_singleton = None
-
-
-def factory():
-    """
-    Factory method to get the singleton instance of DocumentDefinitions.
-
-    Returns:
-        DocumentDefinitions: The singleton instance of document definitions.
-    """
-    global definitions_singleton
-    if definitions_singleton is None:
-        definitions_singleton = initialize_definitions()
-    return definitions_singleton
-
-
-class Document:
-    """
-    Represents a document.
-
-    Attributes:
-        page_id (str): The ID of the page.
-        fields (dict): The fields of the document.
-
-    Raises:
-        ValueError: If the fields do not match the required fields or if a required field is missing.
-    """
-    def __init__(self, page_id: str, fields: dict):
-        definitions = factory()
-        self.page_id = page_id
-        if fields.keys() != definitions.saved_fields.keys():
-            raise ValueError("fields do not match the required fields")
-        for defined_field in definitions.saved_fields.values():
-            if defined_field.required and defined_field.field_name not in fields:
-                raise ValueError(f"field {defined_field.field_name} is required")
-            if defined_field.field_name in fields:
-                setattr(self, defined_field.field_name, fields[defined_field.field_name])
+import json
+import os
+
+DEFINITIONS_FILE = os.getenv("DOCUMENT_DEFINITION_CONFIG", "example-conf.json")
+
+
+class DocumentFieldDefinition:
+    """
+    Represents the definition of a document field.
+
+    Attributes:
+        field_name (str): The name of the field.
+        required (bool): Indicates if the field is required. Default is False.
+    """
+    def __init__(self, field_name: str, required: bool = False):
+        self.field_name = field_name
+        self.required = required
+
+
+class DocumentDefinitions:
+    """
+    Represents the definitions for a document.
+
+    Attributes:
+        saved_fields (dict[str, DocumentFieldDefinition]): A dictionary of saved fields.
+        models (dict[str, str]): A dictionary of models.
+        identifier (str): The identifier field.
+        field_for_llm (str, optional): The field for LLM. Default is None.
+    """
+    def __init__(self, saved_fields: dict[str, DocumentFieldDefinition], models: dict[str, str],
+                 identifier: str, field_for_llm: str = None):
+        self.saved_fields = saved_fields
+        self.models = models
+        self.identifier = identifier
+        self.field_for_llm = field_for_llm
+
+
+def initialize_definitions():
+    """
+    Initializes the document definitions by reading the configuration file.
+
+    Raises:
+        ValueError: If the identifier field is not one of the saved fields or if any model field is not one of the saved fields.
+
+    Returns:
+        DocumentDefinitions: The initialized document definitions.
+    """
+    with open(DEFINITIONS_FILE, 'r', encoding='utf-8') as f:
+        definitions = json.load(f)
+
+        saved_fields = definitions['saved_fields']
+        models = definitions['models']
+        identifier_field = definitions['identifier_field']
+        field_for_llm = definitions.get('field_for_llm', None)
+        if identifier_field not in saved_fields.keys():
+            raise ValueError("identifier_field must be one of the saved fields, check the configuration file")
+
+        for embedded_field in models.values():
+            if embedded_field not in saved_fields.keys():
+                raise ValueError(f"{embedded_field} must be one of the saved fields {saved_fields.keys()}, check the configuration file")
+
+        return DocumentDefinitions(saved_fields, models, identifier_field, field_for_llm)
+
+
+definitions_singleton = None
+
+
+def factory():
+    """
+    Factory method to get the singleton instance of DocumentDefinitions.
+
+    Returns:
+        DocumentDefinitions: The singleton instance of document definitions.
+    """
+    global definitions_singleton
+    if definitions_singleton is None:
+        definitions_singleton = initialize_definitions()
+    return definitions_singleton
+
+
+class Document:
+    """
+    Represents a document.
+
+    Attributes:
+        page_id (str): The ID of the page.
+        fields (dict): The fields of the document.
+
+    Raises:
+        ValueError: If the fields do not match the required fields or if a required field is missing.
+    """
+    def __init__(self, page_id: str, fields: dict):
+        definitions = factory()
+        self.page_id = page_id
+        if fields.keys() != definitions.saved_fields.keys():
+            raise ValueError("fields do not match the required fields")
+        for defined_field in definitions.saved_fields.values():
+            if defined_field.required and defined_field.field_name not in fields:
+                raise ValueError(f"field {defined_field.field_name} is required")
+            if defined_field.field_name in fields:
+                setattr(self, defined_field.field_name, fields[defined_field.field_name])

{kolzchut_ragbot-1.4.1 → kolzchut_ragbot-1.5.0}/kolzchut_ragbot/IntegrateService.py

@@ -1,4 +1,4 @@
-class IntegrateService:
-
-    def on_update_docs(self, _docs):
-        raise NotImplementedError
+class IntegrateService:
+
+    def on_update_docs(self, _docs):
+        raise NotImplementedError

{kolzchut_ragbot-1.4.1 → kolzchut_ragbot-1.5.0}/kolzchut_ragbot/config.py

@@ -1,5 +1,5 @@
-import os
-
-EMBEDDING_INDEX = os.getenv("ES_EMBEDDING_INDEX", "embeddings")
-MODELS_LOCATION = os.getenv("MODELS_LOCATION", "models")
-
+import os
+
+EMBEDDING_INDEX = os.getenv("ES_EMBEDDING_INDEX", "embeddings")
+MODELS_LOCATION = os.getenv("MODELS_LOCATION", "models")
+