ragxo 0.1.5__tar.gz → 0.1.6__tar.gz

{ragxo-0.1.5 → ragxo-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ragxo
-Version: 0.1.5
+Version: 0.1.6
 Summary: A RAG (Retrieval-Augmented Generation) toolkit with Milvus integration
 Home-page: https://github.com/yourusername/ragx
 License: MIT
@@ -26,7 +26,9 @@ Requires-Dist: pymilvus (>=2.5.4,<3.0.0)
 Project-URL: Repository, https://github.com/yourusername/ragx
 Description-Content-Type: text/markdown
 
-# RagXO 🚀
+# RagXO
+
+Export, version and reuse your RAG pipeline everywhere 🚀
 
 [![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)
@@ -49,6 +51,61 @@ RagXO extends the capabilities of traditional RAG (Retrieval-Augmented Generatio
 pip install ragxo
 ```
 
+## Quickstart 🚀
+
+### Build a RAG pipeline
+
+```python
+from ragxo import Ragxo, Document
+
+def preprocess_text_lower(text: str) -> str:
+    return text.lower()
+
+def preprocess_text_remove_special_chars(text: str) -> str:
+    return re.sub(r'[^a-zA-Z0-9\s]', '', text)
+
+def get_embeddings(text: str) -> list[float]:
+    return openai.embeddings.create(text=text, model="text-embedding-ada-002").data[0].embedding
+
+ragxo_client = Ragxo(dimension=768)
+
+ragxo_client.add_preprocess(preprocess_text_lower)
+ragxo_client.add_preprocess(preprocess_text_remove_special_chars)
+ragxo_client.add_embedding_fn(get_embeddings)
+
+ragxo_client.add_system_prompt("You are a helpful assistant that can answer questions about the data provided.")
+ragxo_client.add_model("gpt-4o-mini")
+
+ragxo_client.index([
+    Document(text="Capital of France is Paris", metadata={"source": "example"}, id=1),
+    Document(text="Capital of Germany is Berlin", metadata={"source": "example"}, id=2),
+    Document(text="Capital of Italy is Rome", metadata={"source": "example"}, id=3),
+])
+
+ragxo_client.export("my_rag_v1.0.0")
+
+```
+
+
+### Load a RAG pipeline
+
+```python
+loaded_ragxo_client = Ragxo.load("my_rag_v1.0.0")
+
+results = loaded_ragxo_client.query("What is the capital of France?")
+
+llm_response = loaded_ragxo_client.generate_llm_response(
+    "What is the capital of France?", 
+    limit=10,
+    temperature=0.5, 
+    max_tokens=1000, 
+    top_p=1.0, 
+    frequency_penalty=0.0, 
+    presence_penalty=0.0)
+
+```
+
+
 ## Usage Guide 📚
 
 ### Import

{ragxo-0.1.5 → ragxo-0.1.6}/README.md

@@ -1,4 +1,6 @@
-# RagXO 🚀
+# RagXO
+
+Export, version and reuse your RAG pipeline everywhere 🚀
 
 [![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)
@@ -21,6 +23,61 @@ RagXO extends the capabilities of traditional RAG (Retrieval-Augmented Generatio
 pip install ragxo
 ```
 
+## Quickstart 🚀
+
+### Build a RAG pipeline
+
+```python
+from ragxo import Ragxo, Document
+
+def preprocess_text_lower(text: str) -> str:
+    return text.lower()
+
+def preprocess_text_remove_special_chars(text: str) -> str:
+    return re.sub(r'[^a-zA-Z0-9\s]', '', text)
+
+def get_embeddings(text: str) -> list[float]:
+    return openai.embeddings.create(text=text, model="text-embedding-ada-002").data[0].embedding
+
+ragxo_client = Ragxo(dimension=768)
+
+ragxo_client.add_preprocess(preprocess_text_lower)
+ragxo_client.add_preprocess(preprocess_text_remove_special_chars)
+ragxo_client.add_embedding_fn(get_embeddings)
+
+ragxo_client.add_system_prompt("You are a helpful assistant that can answer questions about the data provided.")
+ragxo_client.add_model("gpt-4o-mini")
+
+ragxo_client.index([
+    Document(text="Capital of France is Paris", metadata={"source": "example"}, id=1),
+    Document(text="Capital of Germany is Berlin", metadata={"source": "example"}, id=2),
+    Document(text="Capital of Italy is Rome", metadata={"source": "example"}, id=3),
+])
+
+ragxo_client.export("my_rag_v1.0.0")
+
+```
+
+
+### Load a RAG pipeline
+
+```python
+loaded_ragxo_client = Ragxo.load("my_rag_v1.0.0")
+
+results = loaded_ragxo_client.query("What is the capital of France?")
+
+llm_response = loaded_ragxo_client.generate_llm_response(
+    "What is the capital of France?", 
+    limit=10,
+    temperature=0.5, 
+    max_tokens=1000, 
+    top_p=1.0, 
+    frequency_penalty=0.0, 
+    presence_penalty=0.0)
+
+```
+
+
 ## Usage Guide 📚
 
 ### Import

{ragxo-0.1.5 → ragxo-0.1.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ragxo"
-version = "0.1.5"
+version = "0.1.6"
 description = "A RAG (Retrieval-Augmented Generation) toolkit with Milvus integration"
 authors = ["Mohamed Sadek <mohamedfawzydes@gmail.com>"]
 readme = "README.md"

{ragxo-0.1.5 → ragxo-0.1.6}/ragxo/client.py

@@ -37,6 +37,10 @@ class Ragxo:
         self.processing_fn.append(fn)
         return self
     
+    def add_llm_response_fn(self, fn: Callable) -> Self:
+        self.llm_response_fn = fn
+        return self
+    
     def add_embedding_fn(self, fn: Callable) -> Self:
         if not fn:
             raise ValueError("Embedding function cannot be None")
@@ -78,7 +82,7 @@ class Ragxo:
         ])
         return self
     
-    def query(self, query: str, output_fields: list[str] = ['text', 'metadata']) -> list[list[dict]]:
+    def query(self, query: str, output_fields: list[str] = ['text', 'metadata'], limit: int = 10) -> list[list[dict]]:
         if not self.embedding_fn:
             raise ValueError("Embedding function not set. Please call add_embedding_fn first.")
             
@@ -91,7 +95,7 @@ class Ragxo:
         return self.client.search(
             collection_name=self.collection_name,
             data=[embedding],
-            limit=10,
+            limit=limit,
             output_fields=output_fields
         )
 
@@ -235,9 +239,18 @@ class Ragxo:
             logger.error(f"Error in S3 load: {e}")
             raise
     
-    def generate_llm_response(self, query: str, data: list[dict] = None) -> ChatCompletion:
+    def generate_llm_response(self, 
+                              query: str, 
+                              limit: int = 10,
+                              data: list[dict] = None, 
+                              temperature: float = 0.5,
+                              max_tokens: int = 1000,
+                              top_p: float = 1.0,
+                              frequency_penalty: float = 0.0,
+                              presence_penalty: float = 0.0,
+                              ) -> ChatCompletion:
         if data is None:
-            data = self.query(query)[0]
+            data = self.query(query, limit=limit)[0]
         
         if not self.system_prompt:
             raise ValueError("System prompt not set. Please call add_system_prompt first.")
@@ -247,7 +260,12 @@ class Ragxo:
             messages=[
                 {"role": "system", "content": self.system_prompt},
                 {"role": "user", "content": "query: {} data: {}".format(query, data)}
-            ]
+            ],
+            temperature=temperature,
+            max_tokens=max_tokens,
+            top_p=top_p,
+            frequency_penalty=frequency_penalty,
+            presence_penalty=presence_penalty,
         )
         
         return response