refactor to r2r (#46)

README.md

@@ -12,8 +12,8 @@ To get started with this project, you'll be using Poetry for managing dependenci
 2. **Clone and Install Dependencies:**
    - Clone the project repository and navigate to the project directory:
      ```bash
-     git clone [email protected]:SciPhi-AI/sciphi_r2r.git
-     cd sciphi_r2r
+     git clone [email protected]:SciPhi-AI/r2r.git
+     cd r2r
      ```
    - Install the project dependencies with Poetry:
      ```bash
@@ -33,7 +33,7 @@ This guide should help you set up the project with minimal hassle. Ensure you fo
 
 ## Demonstration
 
-https://github.com/SciPhi-AI/sciphi_r2r/assets/68796651/c648ab67-973a-416a-985e-2eafb0a41ef0
+https://github.com/SciPhi-AI/r2r/assets/68796651/c648ab67-973a-416a-985e-2eafb0a41ef0
 
 ## Community
 [Join our Discord server!](https://discord.gg/p6KqD2kjtB)
@@ -42,11 +42,11 @@ https://github.com/SciPhi-AI/sciphi_r2r/assets/68796651/c648ab67-973a-416a-985e-
 
 The framework primarily revolves around three core abstractions:
 
-- The **Ingestion Pipeline**: Facilitates the preparation of embeddable 'Documents' from various data formats (json, txt, pdf, html, etc.). The abstraction can be found in [`ingestion.py`](sciphi_r2r/core/pipelines/ingestion.py).
+- The **Ingestion Pipeline**: Facilitates the preparation of embeddable 'Documents' from various data formats (json, txt, pdf, html, etc.). The abstraction can be found in [`ingestion.py`](r2r/core/pipelines/ingestion.py).
 
-- The **Embedding Pipeline**: Manages the transformation of text into stored vector embeddings, interacting with embedding and vector database providers through a series of steps (e.g., extract_text, transform_text, chunk_text, embed_chunks, etc.). The abstraction can be found in [`embedding.py`](sciphi_r2r/core/pipelines/embedding.py).
+- The **Embedding Pipeline**: Manages the transformation of text into stored vector embeddings, interacting with embedding and vector database providers through a series of steps (e.g., extract_text, transform_text, chunk_text, embed_chunks, etc.). The abstraction can be found in [`embedding.py`](r2r/core/pipelines/embedding.py).
 
-- The **RAG Pipeline**: Works similarly to the embedding pipeline but incorporates an LLM provider to produce text completions. The abstraction can be found in [`rag.py`](sciphi_r2r/core/pipelines/rag.py).
+- The **RAG Pipeline**: Works similarly to the embedding pipeline but incorporates an LLM provider to produce text completions. The abstraction can be found in [`rag.py`](r2r/core/pipelines/rag.py).
 
 Each pipeline incorporates a logging database for operation tracking and observability.
 

config.json

@@ -1,7 +1,7 @@
 {
     "logging": {
         "level": "INFO",
-        "name": "sciphi_r2r",
+        "name": "r2r",
         "database": "demo_logs_v1"
     },
     "embedding": {

examples/basic/app.py

@@ -3,17 +3,17 @@
 import dotenv
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
-from sciphi_r2r.core import GenerationConfig, LoggingDatabaseConnection
-from sciphi_r2r.datasets import HuggingFaceDataProvider
-from sciphi_r2r.embeddings import OpenAIEmbeddingProvider
-from sciphi_r2r.llms import OpenAIConfig, OpenAILLM
-from sciphi_r2r.main import create_app, load_config
-from sciphi_r2r.pipelines import (
+from r2r.core import GenerationConfig, LoggingDatabaseConnection
+from r2r.datasets import HuggingFaceDataProvider
+from r2r.embeddings import OpenAIEmbeddingProvider
+from r2r.llms import OpenAIConfig, OpenAILLM
+from r2r.main import create_app, load_config
+from r2r.pipelines import (
     BasicEmbeddingPipeline,
     BasicIngestionPipeline,
     BasicRAGPipeline,
 )
-from sciphi_r2r.vector_dbs import PGVectorDB, QdrantDB
+from r2r.vector_dbs import PGVectorDB, QdrantDB
 
 dotenv.load_dotenv()
 

examples/basic/embedding_pipeline.py

@@ -5,12 +5,12 @@
 import dotenv
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
-from sciphi_r2r.core import DatasetConfig, LoggingDatabaseConnection
-from sciphi_r2r.datasets import HuggingFaceDataProvider
-from sciphi_r2r.embeddings import OpenAIEmbeddingProvider
-from sciphi_r2r.main import load_config
-from sciphi_r2r.pipelines import BasicDocument, BasicEmbeddingPipeline
-from sciphi_r2r.vector_dbs import PGVectorDB, QdrantDB
+from r2r.core import DatasetConfig, LoggingDatabaseConnection
+from r2r.datasets import HuggingFaceDataProvider
+from r2r.embeddings import OpenAIEmbeddingProvider
+from r2r.main import load_config
+from r2r.pipelines import BasicDocument, BasicEmbeddingPipeline
+from r2r.vector_dbs import PGVectorDB, QdrantDB
 
 if __name__ == "__main__":
     dotenv.load_dotenv()

examples/basic/rag_pipeline.py

@@ -4,12 +4,12 @@
 
 import dotenv
 
-from sciphi_r2r.core import GenerationConfig, LoggingDatabaseConnection
-from sciphi_r2r.embeddings import OpenAIEmbeddingProvider
-from sciphi_r2r.llms import OpenAIConfig, OpenAILLM
-from sciphi_r2r.main import load_config
-from sciphi_r2r.pipelines import BasicRAGPipeline
-from sciphi_r2r.vector_dbs import PGVectorDB, QdrantDB
+from r2r.core import GenerationConfig, LoggingDatabaseConnection
+from r2r.embeddings import OpenAIEmbeddingProvider
+from r2r.llms import OpenAIConfig, OpenAILLM
+from r2r.main import load_config
+from r2r.pipelines import BasicRAGPipeline
+from r2r.vector_dbs import PGVectorDB, QdrantDB
 
 
 class DemoRAGPipeline(BasicRAGPipeline):

examples/client/test_client.py

@@ -1,6 +1,6 @@
 import uuid
 
-from sciphi_r2r.client import SciPhiR2RClient
+from r2r.client import SciPhiR2RClient
 
 # Initialize the client with the base URL of your API
 base_url = "http://localhost:8000"  # Change this to your actual API base URL

examples/web_search/rag_pipeline.py

@@ -3,12 +3,12 @@
 
 import dotenv
 
-from sciphi_r2r.core import GenerationConfig, LoggingDatabaseConnection
-from sciphi_r2r.embeddings import OpenAIEmbeddingProvider
-from sciphi_r2r.llms import OpenAIConfig, OpenAILLM
-from sciphi_r2r.main import load_config
-from sciphi_r2r.pipelines import WebSearchRAGPipeline
-from sciphi_r2r.vector_dbs import PGVectorDB, QdrantDB
+from r2r.core import GenerationConfig, LoggingDatabaseConnection
+from r2r.embeddings import OpenAIEmbeddingProvider
+from r2r.llms import OpenAIConfig, OpenAILLM
+from r2r.main import load_config
+from r2r.pipelines import WebSearchRAGPipeline
+from r2r.vector_dbs import PGVectorDB, QdrantDB
 
 vector_db_provider = "qdrant"
 if __name__ == "__main__":

sciphi_r2r/datasets/huggingface/base.py → r2r/datasets/huggingface/base.py

@@ -1,7 +1,7 @@
 import logging
 from typing import Generator, Optional, Tuple
 
-from sciphi_r2r.core import DatasetConfig, DatasetProvider
+from r2r.core import DatasetConfig, DatasetProvider
 
 logger = logging.getLogger(__name__)
 

sciphi_r2r/datasets/pdf/base.py → r2r/datasets/pdf/base.py

@@ -2,7 +2,7 @@
 import os
 from typing import Generator, Optional, Tuple
 
-from sciphi_r2r.core import DatasetConfig, DatasetProvider
+from r2r.core import DatasetConfig, DatasetProvider
 
 logger = logging.getLogger(__name__)
 

sciphi_r2r/embeddings/openai/base.py → r2r/embeddings/openai/base.py

@@ -4,7 +4,7 @@
 
 from openai import OpenAI
 
-from sciphi_r2r.core import EmbeddingProvider
+from r2r.core import EmbeddingProvider
 
 logger = logging.getLogger(__name__)
 

sciphi_r2r/embeddings/setence_transformer/base.py → r2r/embeddings/setence_transformer/base.py

@@ -1,7 +1,7 @@
 import logging
 from typing import Optional
 
-from sciphi_r2r.core import EmbeddingProvider
+from r2r.core import EmbeddingProvider
 
 logger = logging.getLogger(__name__)
 

sciphi_r2r/llms/openai/base.py → r2r/llms/openai/base.py

@@ -6,7 +6,7 @@
 from openai.types import Completion
 from openai.types.chat import ChatCompletion
 
-from sciphi_r2r.core import GenerationConfig, LLMConfig, LLMProvider
+from r2r.core import GenerationConfig, LLMConfig, LLMProvider
 
 logger = logging.getLogger(__name__)
 

sciphi_r2r/main/app.py → r2r/main/app.py

@@ -7,15 +7,15 @@
 from fastapi import FastAPI, File, Form, HTTPException, UploadFile
 from pydantic import BaseModel
 
-from sciphi_r2r.core import (
+from r2r.core import (
     EmbeddingPipeline,
     IngestionPipeline,
     LoggingDatabaseConnection,
     RAGPipeline,
 )
-from sciphi_r2r.main.utils import configure_logging, find_project_root
+from r2r.main.utils import configure_logging, find_project_root
 
-logger = logging.getLogger("sciphi_r2r")
+logger = logging.getLogger("r2r")
 
 # Current directory where this script is located
 CURRENT_DIR = Path(__file__).resolve().parent

sciphi_r2r/main/utils.py → r2r/main/utils.py

@@ -54,12 +54,12 @@ def configure_logging():
         os.makedirs(logs_dir)
 
     # Create a custom logger
-    logger = logging.getLogger("sciphi_r2r")
+    logger = logging.getLogger("r2r")
     logger.setLevel(logging.DEBUG)  # Set the logging level
 
     # Create handlers (console and file handler with rotation)
     c_handler = logging.StreamHandler()
-    log_file_path = os.path.join(logs_dir, "sciphi_r2r.log")
+    log_file_path = os.path.join(logs_dir, "r2r.log")
     f_handler = RotatingFileHandler(
         log_file_path, maxBytes=1000000, backupCount=5
     )

sciphi_r2r/pipelines/basic/embedding.py → r2r/pipelines/basic/embedding.py

@@ -8,14 +8,14 @@
 
 from langchain.text_splitter import TextSplitter
 
-from sciphi_r2r.core import (
+from r2r.core import (
     BasicDocument,
     EmbeddingPipeline,
     LoggingDatabaseConnection,
     VectorDBProvider,
     VectorEntry,
 )
-from sciphi_r2r.embeddings import OpenAIEmbeddingProvider
+from r2r.embeddings import OpenAIEmbeddingProvider
 
 logger = logging.getLogger(__name__)
 

sciphi_r2r/pipelines/basic/ingestion.py → r2r/pipelines/basic/ingestion.py

@@ -8,7 +8,7 @@
 from enum import Enum
 from typing import Optional, Union
 
-from sciphi_r2r.core import (
+from r2r.core import (
     BasicDocument,
     IngestionPipeline,
     LoggingDatabaseConnection,

sciphi_r2r/pipelines/basic/rag.py → r2r/pipelines/basic/rag.py

@@ -4,7 +4,7 @@
 import logging
 from typing import Optional
 
-from sciphi_r2r.core import (
+from r2r.core import (
     GenerationConfig,
     LLMProvider,
     LoggingDatabaseConnection,
@@ -13,7 +13,7 @@
     VectorSearchResult,
     log_execution_to_db,
 )
-from sciphi_r2r.embeddings import OpenAIEmbeddingProvider
+from r2r.embeddings import OpenAIEmbeddingProvider
 
 logger = logging.getLogger(__name__)
 

sciphi_r2r/pipelines/web_search/rag.py → r2r/pipelines/web_search/rag.py

@@ -4,15 +4,15 @@
 import logging
 from typing import Optional
 
-from sciphi_r2r.core import (
+from r2r.core import (
     GenerationConfig,
     LLMProvider,
     LoggingDatabaseConnection,
     VectorDBProvider,
     log_execution_to_db,
 )
-from sciphi_r2r.embeddings import OpenAIEmbeddingProvider
-from sciphi_r2r.integrations import SerperClient
+from r2r.embeddings import OpenAIEmbeddingProvider
+from r2r.integrations import SerperClient
 
 from ..basic.rag import BasicRAGPipeline
 

sciphi_r2r/vector_dbs/pg_vector/base.py → r2r/vector_dbs/pg_vector/base.py

@@ -2,9 +2,9 @@
 import os
 from typing import Optional, Union
 
-from sciphi_r2r.core import VectorDBProvider, VectorEntry, VectorSearchResult
-from sciphi_r2r.vecs.client import Client
-from sciphi_r2r.vecs.collection import Collection
+from r2r.core import VectorDBProvider, VectorEntry, VectorSearchResult
+from r2r.vecs.client import Client
+from r2r.vecs.collection import Collection
 
 logger = logging.getLogger(__name__)
 
@@ -21,7 +21,7 @@ def __init__(self, provider: str = "pgvector") -> None:
                 "PGVectorDB must be initialized with provider `pgvector`."
             )
         try:
-            import sciphi_r2r.vecs
+            import r2r.vecs
         except ImportError:
             raise ValueError(
                 f"Error, PGVectorDB requires the vecs library. Please run `poetry add vecs`."
@@ -36,7 +36,7 @@ def __init__(self, provider: str = "pgvector") -> None:
             DB_CONNECTION = (
                 f"postgresql://{user}:{password}@{host}:{port}/{db_name}"
             )
-            self.vx: Client = sciphi_r2r.vecs.create_client(DB_CONNECTION)
+            self.vx: Client = r2r.vecs.create_client(DB_CONNECTION)
         except Exception as e:
             raise ValueError(
                 f"Error {e} occurred while attempting to connect to the pgvector provider with {DB_CONNECTION}."

sciphi_r2r/vector_dbs/qdrant/base.py → r2r/vector_dbs/qdrant/base.py

@@ -2,7 +2,7 @@
 import os
 from typing import Optional, Union
 
-from sciphi_r2r.core import VectorDBProvider, VectorEntry, VectorSearchResult
+from r2r.core import VectorDBProvider, VectorEntry, VectorSearchResult
 
 logger = logging.getLogger(__name__)