ragxo 0.1.1__tar.gz → 0.1.3__tar.gz

ragxo-0.1.3/PKG-INFO

@@ -0,0 +1,212 @@
+Metadata-Version: 2.1
+Name: ragxo
+Version: 0.1.3
+Summary: A RAG (Retrieval-Augmented Generation) toolkit with Milvus integration
+Home-page: https://github.com/yourusername/ragx
+License: MIT
+Keywords: rag,milvus,nlp,embeddings,openai
+Author: Mohamed Sadek
+Author-email: mohamedfawzydes@gmail.com
+Requires-Python: >=3.11,<4.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: dill (>=0.3.9,<0.4.0)
+Requires-Dist: milvus (>=2.3.9,<3.0.0)
+Requires-Dist: openai (>=1.61.1,<2.0.0)
+Requires-Dist: pydantic (>=2.10.6,<3.0.0)
+Requires-Dist: pymilvus (>=2.5.4,<3.0.0)
+Project-URL: Repository, https://github.com/yourusername/ragx
+Description-Content-Type: text/markdown
+
+# RagXO 🚀
+
+[![PyPI version](https://badge.fury.io/py/ragxo.svg)](https://badge.fury.io/py/ragxo)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/release/python-380/)
+
+RagXO extends the capabilities of traditional RAG (Retrieval-Augmented Generation) systems by providing a unified way to package, version, and deploy your entire RAG pipeline with LLM integration. Export your complete system—including embedding functions, preprocessing steps, vector store, and LLM configurations—into a single, portable artifact.
+
+## Features ✨
+
+- **Complete RAG Pipeline**: Package your entire RAG system into a versioned artifact
+- **LLM Integration**: Built-in support for OpenAI models
+- **Flexible Embedding**: Compatible with any embedding function (Sentence Transformers, OpenAI, etc.)
+- **Custom Preprocessing**: Chain multiple preprocessing steps
+- **Vector Store Integration**: Built-in Milvus support
+- **System Prompts**: Include and version your system prompts
+
+## Installation 🛠️
+
+```bash
+pip install ragxo
+```
+
+## Quick Start 🚀
+
+```python
+from ragxo import Ragxo, Document
+from openai import OpenAI
+client = OpenAI()
+
+def get_openai_embeddings(text: str) -> list[float]:
+    response = client.embeddings.create(
+        input=text,
+        model="text-embedding-ada-002"
+    )
+    return response.data[0].embedding
+
+def preprocess_text(text: str) -> str:
+    return text.lower()
+
+# Initialize and configure RagXO
+ragxo = Ragxo(dimension=384)
+ragxo.add_preprocess(preprocess_text)
+ragxo.add_embedding_fn(get_openai_embeddings)
+
+# Add system prompt and model
+ragxo.add_system_prompt("You are a helpful assistant.")
+ragxo.add_model("gpt-4o-mini")
+
+# Create and index documents
+documents = [
+    Document(
+        text="Sample document for indexing",
+        metadata={"source": "example"},
+        id=1
+    )
+]
+ragxo.index(documents)
+
+# Export the pipeline
+ragxo.export("my_rag_v1")
+
+# Load and use elsewhere
+loaded_ragxo = Ragxo.load("my_rag_v1")
+
+# Query and generate response
+similar_docs = loaded_ragxo.query("sample query")
+llm_response = loaded_ragxo.generate_llm_response("What can you tell me about the sample?")
+```
+
+## Usage Guide 📚
+
+### Creating Documents
+
+```python
+from ragxo import Document
+
+doc = Document(
+    text="Your document content here",
+    metadata={"source": "wiki", "category": "science"},
+    id=1
+)
+```
+
+### Adding Preprocessing Steps
+
+```python
+import re
+
+def remove_special_chars(text: str) -> str:
+    return re.sub(r'[^a-zA-Z0-9\s]', '', text)
+
+def lowercase(text: str) -> str:
+    return text.lower()
+
+ragxo.add_preprocess(remove_special_chars)
+ragxo.add_preprocess(lowercase)
+```
+
+### Custom Embedding Functions
+
+```python
+# Using SentenceTransformers
+from sentence_transformers import SentenceTransformer
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def get_embeddings(text: str) -> list[float]:
+    return model.encode(text).tolist()
+
+ragxo.add_embedding_fn(get_embeddings)
+
+# Or using OpenAI
+from openai import OpenAI
+client = OpenAI()
+
+def get_openai_embeddings(text: str) -> list[float]:
+    response = client.embeddings.create(
+        input=text,
+        model="text-embedding-ada-002"
+    )
+    return response.data[0].embedding
+
+ragxo.add_embedding_fn(get_openai_embeddings)
+```
+
+### LLM Configuration
+
+```python
+# Set system prompt
+ragxo.add_system_prompt("""
+You are a helpful assistant. Use the provided context to answer questions accurately.
+If you're unsure about something, please say so.
+""")
+
+# Set LLM model
+ragxo.add_model("gpt-4")
+```
+
+### Export and Load
+
+```python
+# Export your RAG pipeline
+ragxo.export("rag_pipeline_v1")
+
+# Load it elsewhere
+loaded_ragxo = Ragxo.load("rag_pipeline_v1")
+```
+
+## Best Practices 💡
+
+1. **Version Your Exports**: Use semantic versioning for your exports:
+```python
+ragxo.export("my_rag_v1.0.0")
+```
+
+2. **Validate After Loading**: Always test your loaded pipeline:
+```python
+loaded_ragxo = Ragxo.load("my_rag")
+try:
+    # Test similarity search
+    similar_docs = loaded_ragxo.query("test query")
+    # Test LLM generation
+    llm_response = loaded_ragxo.generate_llm_response("test question")
+    print("Pipeline loaded successfully!")
+except Exception as e:
+    print(f"Error loading pipeline: {e}")
+```
+
+3. **Document Your Pipeline Configuration**: Keep track of your setup:
+```python
+pipeline_config = {
+    "preprocessing_steps": ["remove_special_chars", "lowercase"],
+    "embedding_model": "all-MiniLM-L6-v2",
+    "llm_model": "gpt-4",
+    "dimension": 384
+}
+```
+
+## License 📝
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Contributing 🤝
+
+Contributions are welcome! Please feel free to submit a Pull Request.

ragxo-0.1.3/README.md

@@ -0,0 +1,185 @@
+# RagXO 🚀
+
+[![PyPI version](https://badge.fury.io/py/ragxo.svg)](https://badge.fury.io/py/ragxo)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/release/python-380/)
+
+RagXO extends the capabilities of traditional RAG (Retrieval-Augmented Generation) systems by providing a unified way to package, version, and deploy your entire RAG pipeline with LLM integration. Export your complete system—including embedding functions, preprocessing steps, vector store, and LLM configurations—into a single, portable artifact.
+
+## Features ✨
+
+- **Complete RAG Pipeline**: Package your entire RAG system into a versioned artifact
+- **LLM Integration**: Built-in support for OpenAI models
+- **Flexible Embedding**: Compatible with any embedding function (Sentence Transformers, OpenAI, etc.)
+- **Custom Preprocessing**: Chain multiple preprocessing steps
+- **Vector Store Integration**: Built-in Milvus support
+- **System Prompts**: Include and version your system prompts
+
+## Installation 🛠️
+
+```bash
+pip install ragxo
+```
+
+## Quick Start 🚀
+
+```python
+from ragxo import Ragxo, Document
+from openai import OpenAI
+client = OpenAI()
+
+def get_openai_embeddings(text: str) -> list[float]:
+    response = client.embeddings.create(
+        input=text,
+        model="text-embedding-ada-002"
+    )
+    return response.data[0].embedding
+
+def preprocess_text(text: str) -> str:
+    return text.lower()
+
+# Initialize and configure RagXO
+ragxo = Ragxo(dimension=384)
+ragxo.add_preprocess(preprocess_text)
+ragxo.add_embedding_fn(get_openai_embeddings)
+
+# Add system prompt and model
+ragxo.add_system_prompt("You are a helpful assistant.")
+ragxo.add_model("gpt-4o-mini")
+
+# Create and index documents
+documents = [
+    Document(
+        text="Sample document for indexing",
+        metadata={"source": "example"},
+        id=1
+    )
+]
+ragxo.index(documents)
+
+# Export the pipeline
+ragxo.export("my_rag_v1")
+
+# Load and use elsewhere
+loaded_ragxo = Ragxo.load("my_rag_v1")
+
+# Query and generate response
+similar_docs = loaded_ragxo.query("sample query")
+llm_response = loaded_ragxo.generate_llm_response("What can you tell me about the sample?")
+```
+
+## Usage Guide 📚
+
+### Creating Documents
+
+```python
+from ragxo import Document
+
+doc = Document(
+    text="Your document content here",
+    metadata={"source": "wiki", "category": "science"},
+    id=1
+)
+```
+
+### Adding Preprocessing Steps
+
+```python
+import re
+
+def remove_special_chars(text: str) -> str:
+    return re.sub(r'[^a-zA-Z0-9\s]', '', text)
+
+def lowercase(text: str) -> str:
+    return text.lower()
+
+ragxo.add_preprocess(remove_special_chars)
+ragxo.add_preprocess(lowercase)
+```
+
+### Custom Embedding Functions
+
+```python
+# Using SentenceTransformers
+from sentence_transformers import SentenceTransformer
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def get_embeddings(text: str) -> list[float]:
+    return model.encode(text).tolist()
+
+ragxo.add_embedding_fn(get_embeddings)
+
+# Or using OpenAI
+from openai import OpenAI
+client = OpenAI()
+
+def get_openai_embeddings(text: str) -> list[float]:
+    response = client.embeddings.create(
+        input=text,
+        model="text-embedding-ada-002"
+    )
+    return response.data[0].embedding
+
+ragxo.add_embedding_fn(get_openai_embeddings)
+```
+
+### LLM Configuration
+
+```python
+# Set system prompt
+ragxo.add_system_prompt("""
+You are a helpful assistant. Use the provided context to answer questions accurately.
+If you're unsure about something, please say so.
+""")
+
+# Set LLM model
+ragxo.add_model("gpt-4")
+```
+
+### Export and Load
+
+```python
+# Export your RAG pipeline
+ragxo.export("rag_pipeline_v1")
+
+# Load it elsewhere
+loaded_ragxo = Ragxo.load("rag_pipeline_v1")
+```
+
+## Best Practices 💡
+
+1. **Version Your Exports**: Use semantic versioning for your exports:
+```python
+ragxo.export("my_rag_v1.0.0")
+```
+
+2. **Validate After Loading**: Always test your loaded pipeline:
+```python
+loaded_ragxo = Ragxo.load("my_rag")
+try:
+    # Test similarity search
+    similar_docs = loaded_ragxo.query("test query")
+    # Test LLM generation
+    llm_response = loaded_ragxo.generate_llm_response("test question")
+    print("Pipeline loaded successfully!")
+except Exception as e:
+    print(f"Error loading pipeline: {e}")
+```
+
+3. **Document Your Pipeline Configuration**: Keep track of your setup:
+```python
+pipeline_config = {
+    "preprocessing_steps": ["remove_special_chars", "lowercase"],
+    "embedding_model": "all-MiniLM-L6-v2",
+    "llm_model": "gpt-4",
+    "dimension": 384
+}
+```
+
+## License 📝
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Contributing 🤝
+
+Contributions are welcome! Please feel free to submit a Pull Request.

{ragxo-0.1.1 → ragxo-0.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ragxo"
-version = "0.1.1"
+version = "0.1.3"
 description = "A RAG (Retrieval-Augmented Generation) toolkit with Milvus integration"
 authors = ["Mohamed Sadek <mohamedfawzydes@gmail.com>"]
 readme = "README.md"
@@ -23,8 +23,6 @@ python = "^3.11"
 milvus = "^2.3.9"
 pymilvus = "^2.5.4"
 pydantic = "^2.10.6"
-nltk = "^3.9.1"
-sentence-transformers = "^3.4.1"
 dill = "^0.3.9"
 openai = "^1.61.1"
 

{ragxo-0.1.1 → ragxo-0.1.3}/ragxo/ragx.py

@@ -126,7 +126,11 @@ class Ragxo:
             logger.error(f"Error in load: {e}")
             raise
     
-    def generate_llm_response(self, query: str) -> ChatCompletion:
+    def generate_llm_response(self, query: str, data: list[dict] = None) -> ChatCompletion:
+        
+        if data is None:
+            data = self.query(query)[0]
+        
         if not self.system_prompt:
             raise ValueError("System prompt not set. Please call add_system_prompt first.")
         
@@ -134,7 +138,7 @@ class Ragxo:
             model=self.model,
             messages=[
                 {"role": "system", "content": self.system_prompt},
-                {"role": "user", "content": query}
+                {"role": "user", "content": "query: {} data: {}".format(query, data)}
             ]
         )
         

ragxo-0.1.1/PKG-INFO

@@ -1,30 +0,0 @@
-Metadata-Version: 2.1
-Name: ragxo
-Version: 0.1.1
-Summary: A RAG (Retrieval-Augmented Generation) toolkit with Milvus integration
-Home-page: https://github.com/yourusername/ragx
-License: MIT
-Keywords: rag,milvus,nlp,embeddings,openai
-Author: Mohamed Sadek
-Author-email: mohamedfawzydes@gmail.com
-Requires-Python: >=3.11,<4.0
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Dist: dill (>=0.3.9,<0.4.0)
-Requires-Dist: milvus (>=2.3.9,<3.0.0)
-Requires-Dist: nltk (>=3.9.1,<4.0.0)
-Requires-Dist: openai (>=1.61.1,<2.0.0)
-Requires-Dist: pydantic (>=2.10.6,<3.0.0)
-Requires-Dist: pymilvus (>=2.5.4,<3.0.0)
-Requires-Dist: sentence-transformers (>=3.4.1,<4.0.0)
-Project-URL: Repository, https://github.com/yourusername/ragx
-Description-Content-Type: text/markdown
-
-