ragit 0.8.2__tar.gz → 0.11.0__tar.gz

{ragit-0.8.2/ragit.egg-info → ragit-0.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ragit
-Version: 0.8.2
+Version: 0.11.0
 Summary: Automatic RAG Pattern Optimization Engine
 Author: RODMENA LIMITED
 Maintainer-email: RODMENA LIMITED <info@rodmena.co.uk>
@@ -16,18 +16,16 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: POSIX :: Linux
-Requires-Python: <3.14,>=3.12
+Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: requests>=2.31.0
 Requires-Dist: numpy>=1.26.0
-Requires-Dist: pandas>=2.2.0
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: python-dotenv>=1.0.0
-Requires-Dist: scikit-learn>=1.5.0
 Requires-Dist: tqdm>=4.66.0
-Requires-Dist: trio>=0.24.0
 Requires-Dist: httpx>=0.27.0
+Requires-Dist: resilient-circuit>=0.4.7
 Provides-Extra: dev
 Requires-Dist: ragit[test]; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
@@ -39,8 +37,6 @@ Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-cov; extra == "test"
 Requires-Dist: pytest-mock; extra == "test"
-Provides-Extra: transformers
-Requires-Dist: sentence-transformers>=2.2.0; extra == "transformers"
 Provides-Extra: docs
 Requires-Dist: sphinx>=7.0; extra == "docs"
 Requires-Dist: sphinx-rtd-theme>=2.0; extra == "docs"
@@ -55,14 +51,11 @@ RAG toolkit for Python. Document loading, chunking, vector search, LLM integrati
 
 ```bash
 pip install ragit
-
-# For offline embedding
-pip install ragit[transformers]
 ```
 
 ## Quick Start
 
-You must provide an embedding source: custom function, SentenceTransformers, or any provider.
+You must provide an embedding source: custom function, Ollama, or any provider.
 
 ### Custom Embedding Function
 
@@ -90,26 +83,17 @@ assistant = RAGAssistant("docs/", embed_fn=my_embed, generate_fn=my_generate)
 answer = assistant.ask("How does authentication work?")
 ```
 
-### Offline Embedding (SentenceTransformers)
-
-Models are downloaded automatically on first use (~90MB for default model).
+### With Ollama (nomic-embed-text)
 
 ```python
 from ragit import RAGAssistant
-from ragit.providers import SentenceTransformersProvider
+from ragit.providers import OllamaProvider
 
-# Uses all-MiniLM-L6-v2 by default
-assistant = RAGAssistant("docs/", provider=SentenceTransformersProvider())
-
-# Or specify a model
-assistant = RAGAssistant(
-    "docs/",
-    provider=SentenceTransformersProvider(model_name="all-mpnet-base-v2")
-)
+# Uses nomic-embed-text for embeddings (768d)
+assistant = RAGAssistant("docs/", provider=OllamaProvider())
+results = assistant.retrieve("search query")
 ```
 
-Available models: `all-MiniLM-L6-v2` (384d), `all-mpnet-base-v2` (768d), `paraphrase-MiniLM-L6-v2` (384d)
-
 ## Core API
 
 ```python
@@ -128,6 +112,45 @@ answer = assistant.ask(question, top_k=3)         # Requires generate_fn/LLM
 code = assistant.generate_code(request)           # Requires generate_fn/LLM
 ```
 
+## Index Persistence
+
+Save and load indexes to avoid re-computing embeddings:
+
+```python
+# Save index to disk
+assistant.save_index("./my_index")
+
+# Load index later (much faster than re-indexing)
+loaded = RAGAssistant.load_index("./my_index", provider=OllamaProvider())
+results = loaded.retrieve("query")
+```
+
+## Thread Safety
+
+RAGAssistant is thread-safe. Multiple threads can safely read while another writes:
+
+```python
+import threading
+
+assistant = RAGAssistant("docs/", provider=OllamaProvider())
+
+# Safe: concurrent reads and writes
+threading.Thread(target=lambda: assistant.retrieve("query")).start()
+threading.Thread(target=lambda: assistant.add_documents([new_doc])).start()
+```
+
+## Resource Management
+
+Use context managers for automatic cleanup:
+
+```python
+from ragit.providers import OllamaProvider
+
+with OllamaProvider() as provider:
+    response = provider.generate("Hello", model="llama3")
+# Session automatically closed
+```
+
 ## Document Loading
 
 ```python

{ragit-0.8.2 → ragit-0.11.0}/README.md

@@ -6,14 +6,11 @@ RAG toolkit for Python. Document loading, chunking, vector search, LLM integrati
 
 ```bash
 pip install ragit
-
-# For offline embedding
-pip install ragit[transformers]
 ```
 
 ## Quick Start
 
-You must provide an embedding source: custom function, SentenceTransformers, or any provider.
+You must provide an embedding source: custom function, Ollama, or any provider.
 
 ### Custom Embedding Function
 
@@ -41,26 +38,17 @@ assistant = RAGAssistant("docs/", embed_fn=my_embed, generate_fn=my_generate)
 answer = assistant.ask("How does authentication work?")
 ```
 
-### Offline Embedding (SentenceTransformers)
-
-Models are downloaded automatically on first use (~90MB for default model).
+### With Ollama (nomic-embed-text)
 
 ```python
 from ragit import RAGAssistant
-from ragit.providers import SentenceTransformersProvider
+from ragit.providers import OllamaProvider
 
-# Uses all-MiniLM-L6-v2 by default
-assistant = RAGAssistant("docs/", provider=SentenceTransformersProvider())
-
-# Or specify a model
-assistant = RAGAssistant(
-    "docs/",
-    provider=SentenceTransformersProvider(model_name="all-mpnet-base-v2")
-)
+# Uses nomic-embed-text for embeddings (768d)
+assistant = RAGAssistant("docs/", provider=OllamaProvider())
+results = assistant.retrieve("search query")
 ```
 
-Available models: `all-MiniLM-L6-v2` (384d), `all-mpnet-base-v2` (768d), `paraphrase-MiniLM-L6-v2` (384d)
-
 ## Core API
 
 ```python
@@ -79,6 +67,45 @@ answer = assistant.ask(question, top_k=3)         # Requires generate_fn/LLM
 code = assistant.generate_code(request)           # Requires generate_fn/LLM
 ```
 
+## Index Persistence
+
+Save and load indexes to avoid re-computing embeddings:
+
+```python
+# Save index to disk
+assistant.save_index("./my_index")
+
+# Load index later (much faster than re-indexing)
+loaded = RAGAssistant.load_index("./my_index", provider=OllamaProvider())
+results = loaded.retrieve("query")
+```
+
+## Thread Safety
+
+RAGAssistant is thread-safe. Multiple threads can safely read while another writes:
+
+```python
+import threading
+
+assistant = RAGAssistant("docs/", provider=OllamaProvider())
+
+# Safe: concurrent reads and writes
+threading.Thread(target=lambda: assistant.retrieve("query")).start()
+threading.Thread(target=lambda: assistant.add_documents([new_doc])).start()
+```
+
+## Resource Management
+
+Use context managers for automatic cleanup:
+
+```python
+from ragit.providers import OllamaProvider
+
+with OllamaProvider() as provider:
+    response = provider.generate("Hello", model="llama3")
+# Session automatically closed
+```
+
 ## Document Loading
 
 ```python

{ragit-0.8.2 → ragit-0.11.0}/pyproject.toml

@@ -10,7 +10,7 @@ maintainers = [
     { name = "RODMENA LIMITED", email = "info@rodmena.co.uk" },
 ]
 readme = "README.md"
-requires-python = ">=3.12,<3.14"
+requires-python = ">=3.12"
 classifiers = [
     "Development Status :: 2 - Pre-Alpha",
     "Natural Language :: English",
@@ -33,13 +33,11 @@ dynamic = ["version"]
 dependencies = [
     "requests>=2.31.0",
     "numpy>=1.26.0",
-    "pandas>=2.2.0",
     "pydantic>=2.0.0",
     "python-dotenv>=1.0.0",
-    "scikit-learn>=1.5.0",
     "tqdm>=4.66.0",
-    "trio>=0.24.0",
     "httpx>=0.27.0",
+    "resilient-circuit>=0.4.7",
 ]
 
 [project.urls]
@@ -59,8 +57,6 @@ dev = [
 
 test = ["pytest", "pytest-cov", "pytest-mock"]
 
-transformers = ["sentence-transformers>=2.2.0"]
-
 docs = [
     "sphinx>=7.0",
     "sphinx-rtd-theme>=2.0",

{ragit-0.8.2 → ragit-0.11.0}/ragit/__init__.py

@@ -16,11 +16,7 @@ Quick Start
 >>> assistant = RAGAssistant("docs/", embed_fn=my_embed)
 >>> results = assistant.retrieve("How do I create a REST API?")
 >>>
->>> # With SentenceTransformers (offline, requires ragit[transformers])
->>> from ragit.providers import SentenceTransformersProvider
->>> assistant = RAGAssistant("docs/", provider=SentenceTransformersProvider())
->>>
->>> # With Ollama (explicit)
+>>> # With Ollama
 >>> from ragit.providers import OllamaProvider
 >>> assistant = RAGAssistant("docs/", provider=OllamaProvider())
 >>> answer = assistant.ask("How do I create a REST API?")
@@ -63,14 +59,27 @@ from ragit.core.experiment.experiment import (  # noqa: E402
     RagitExperiment,
 )
 from ragit.core.experiment.results import EvaluationResult, ExperimentResults  # noqa: E402
+from ragit.exceptions import (  # noqa: E402
+    ConfigurationError,
+    EvaluationError,
+    ExceptionAggregator,
+    GenerationError,
+    IndexingError,
+    ProviderError,
+    RagitError,
+    RetrievalError,
+)
 from ragit.loaders import (  # noqa: E402
     chunk_by_separator,
     chunk_document,
     chunk_rst_sections,
     chunk_text,
+    deduplicate_documents,
+    generate_document_id,
     load_directory,
     load_text,
 )
+from ragit.monitor import ExecutionMonitor  # noqa: E402
 from ragit.providers import (  # noqa: E402
     BaseEmbeddingProvider,
     BaseLLMProvider,
@@ -89,6 +98,8 @@ __all__ = [
     "chunk_document",
     "chunk_by_separator",
     "chunk_rst_sections",
+    "generate_document_id",
+    "deduplicate_documents",
     # Core classes
     "Document",
     "Chunk",
@@ -97,6 +108,17 @@ __all__ = [
     "FunctionProvider",
     "BaseLLMProvider",
     "BaseEmbeddingProvider",
+    # Exceptions
+    "RagitError",
+    "ConfigurationError",
+    "ProviderError",
+    "IndexingError",
+    "RetrievalError",
+    "GenerationError",
+    "EvaluationError",
+    "ExceptionAggregator",
+    # Monitoring
+    "ExecutionMonitor",
     # Optimization
     "RagitExperiment",
     "BenchmarkQuestion",
@@ -104,13 +126,3 @@ __all__ = [
     "EvaluationResult",
     "ExperimentResults",
 ]
-
-# Conditionally add SentenceTransformersProvider if available
-try:
-    from ragit.providers import (  # noqa: E402
-        SentenceTransformersProvider as SentenceTransformersProvider,
-    )
-
-    __all__ += ["SentenceTransformersProvider"]
-except ImportError:
-    pass