amsdal_ml 0.1.3__py3-none-any.whl → 0.2.0__py3-none-any.whl

amsdal_ml-0.2.0.dist-info/METADATA

@@ -0,0 +1,293 @@
+Metadata-Version: 2.4
+Name: amsdal_ml
+Version: 0.2.0
+Summary: amsdal_ml plugin for AMSDAL Framework
+Requires-Python: >=3.11
+Requires-Dist: aiohttp==3.12.15
+Requires-Dist: amsdal-cli>=0.5.7
+Requires-Dist: amsdal-data>=0.5.9
+Requires-Dist: amsdal-models>=0.5.9
+Requires-Dist: amsdal-utils>=0.5.4
+Requires-Dist: amsdal>=0.5.6
+Requires-Dist: mcp>=0.1
+Requires-Dist: openai==1.100.2
+Requires-Dist: pydantic-settings==2.10.1
+Requires-Dist: pydantic==2.11.7
+Requires-Dist: pymupdf>=1.24.10
+Description-Content-Type: text/markdown
+
+# AMSDAL ML
+
+[![CI](https://github.com/amsdal/amsdal_ml/actions/workflows/ci.yml/badge.svg)](https://github.com/amsdal/amsdal_ml/actions/workflows/ci.yml)
+[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
+
+Machine learning plugin for the AMSDAL Framework, providing embeddings, vector search, semantic retrieval, and AI agents with support for OpenAI models.
+
+## Features
+
+- **Vector Embeddings**: Generate and store embeddings for any AMSDAL model with automatic chunking
+- **Semantic Search**: Query your data using natural language with tag-based filtering
+- **AI Agents**: Build Q&A systems with streaming support and citation tracking
+- **Async-First**: Optimized for high-performance async operations
+- **MCP Integration**: Expose and consume tools via Model Context Protocol (stdio/HTTP)
+- **File Attachments**: Process and embed documents with built-in loaders
+- **Extensible**: Abstract base classes for custom models, retrievers, and ingesters
+
+## Installation
+
+```bash
+pip install amsdal-ml
+```
+
+### Requirements
+
+- Python 3.11 or higher
+- AMSDAL Framework 0.5.6+
+- OpenAI API key (for default implementations)
+
+## Quick Start
+
+### 1. Configuration
+
+Create a `.env` file in your project root:
+
+```env
+OPENAI_API_KEY=sk-your-api-key-here
+async_mode=true
+ml_model_class=amsdal_ml.ml_models.openai_model.OpenAIModel
+ml_retriever_class=amsdal_ml.ml_retrievers.openai_retriever.OpenAIRetriever
+ml_ingesting_class=amsdal_ml.ml_ingesting.openai_ingesting.OpenAIIngesting
+```
+
+Create a `config.yml` for AMSDAL connections:
+
+```yaml
+application_name: my-ml-app
+async_mode: true
+connections:
+  - name: sqlite_state
+    backend: sqlite-state-async
+    credentials:
+      - db_path: ./warehouse/state.sqlite3
+      - check_same_thread: false
+  - name: lock
+    backend: amsdal_data.lock.implementations.thread_lock.ThreadLock
+resources_config:
+  repository:
+    default: sqlite_state
+  lock: lock
+```
+
+### 2. Generate Embeddings
+
+```python
+from amsdal_ml.ml_ingesting.openai_ingesting import OpenAIIngesting
+from amsdal_ml.ml_config import ml_config
+
+# Initialize ingesting
+ingester = OpenAIIngesting(
+    model=MyModel,
+    embedding_field='embedding',
+)
+
+# Generate embeddings for an instance
+instance = MyModel(content='Your text here')
+embeddings = await ingester.agenerate_embeddings(instance)
+await ingester.asave(embeddings, instance)
+```
+
+### 3. Semantic Search
+
+```python
+from amsdal_ml.ml_retrievers.openai_retriever import OpenAIRetriever
+
+retriever = OpenAIRetriever()
+
+# Search for relevant content
+results = await retriever.asimilarity_search(
+    query='What is machine learning?',
+    k=5,
+    include_tags=['documentation']
+)
+
+for chunk in results:
+    print(f'{chunk.object_class}:{chunk.object_id} - {chunk.raw_text}')
+```
+
+### 4. Build an AI Agent
+
+```python
+from amsdal_ml.agents.default_qa_agent import DefaultQAAgent
+
+agent = DefaultQAAgent()
+
+# Ask questions
+output = await agent.arun('Explain vector embeddings')
+print(output.answer)
+print(f'Used tools: {output.used_tools}')
+
+# Stream responses
+async for chunk in agent.astream('What is semantic search?'):
+    print(chunk, end='', flush=True)
+```
+
+### 5. Functional Calling Agent with Python Tools
+
+```python
+from amsdal_ml.agents.functional_calling_agent import FunctionalCallingAgent
+from amsdal_ml.agents.python_tool import PythonTool
+from amsdal_ml.ml_models.openai_model import OpenAIModel
+
+llm = OpenAIModel()
+agent = FunctionalCallingAgent(model=llm, tools=[search_tool, render_tool])
+result = await agent.arun(user_query="Find products with price > 100", history=[])
+```
+
+### 6. Natural Language Query Retriever
+
+```python
+from amsdal_ml.ml_retrievers.query_retriever import NLQueryRetriever
+
+retriever = NLQueryRetriever(llm=llm, queryset=Product.objects.all())
+documents = await retriever.invoke("Show me red products", limit=10)
+```
+
+### 7. Document Ingestion Pipeline
+
+```python
+from amsdal_ml.ml_ingesting import ModelIngester
+from amsdal_ml.ml_ingesting.pipeline import DefaultIngestionPipeline
+from amsdal_ml.ml_ingesting.loaders.pdf_loader import PdfLoader
+from amsdal_ml.ml_ingesting.processors.text_cleaner import TextCleaner
+from amsdal_ml.ml_ingesting.splitters.token_splitter import TokenSplitter
+from amsdal_ml.ml_ingesting.embedders.openai_embedder import OpenAIEmbedder
+from amsdal_ml.ml_ingesting.stores.embedding_data import EmbeddingDataStore
+
+pipeline = DefaultIngestionPipeline(
+    loader=PdfLoader(),  # Uses pymupdf for PDF processing
+    cleaner=TextCleaner(),
+    splitter=TokenSplitter(max_tokens=800, overlap_tokens=80),
+    embedder=OpenAIEmbedder(),
+    store=EmbeddingDataStore(),
+)
+
+ingester = ModelIngester(
+    pipeline=pipeline,
+    base_tags=["document"],
+    base_metadata={"source": "pdf"},
+)
+```
+
+## Architecture
+
+### Core Components
+
+- **`MLModel`**: Abstract interface for LLM inference (invoke, stream, with attachments)
+- **`MLIngesting`**: Generate text and embeddings from data objects with chunking
+- **`MLRetriever`**: Semantic similarity search with tag-based filtering
+- **`Agent`**: Q&A and task-oriented agents with streaming and citations
+- **`EmbeddingModel`**: Database model storing 1536-dimensional vectors linked to source objects
+- **`PythonTool`**: Tool for executing Python functions within agents
+- **`FunctionalCallingAgent`**: Agent specialized in functional calling with configurable tools
+- **`NLQueryRetriever`**: Retriever for natural language queries on AMSDAL querysets
+- **`DefaultIngestionPipeline`**: Pipeline for document ingestion including loader, cleaner, splitter, embedder, and store
+- **`ModelIngester`**: High-level ingester for processing models with customizable pipelines and metadata
+- **`PdfLoader`**: Document loader using pymupdf for PDF processing
+- **`TextCleaner`**: Processor for cleaning and normalizing text
+- **`TokenSplitter`**: Splitter for dividing text into chunks based on token count
+- **`OpenAIEmbedder`**: Embedder for generating embeddings via OpenAI API
+- **`EmbeddingDataStore`**: Store for saving embedding data linked to source objects
+- **MCP Server/Client**: Expose retrievers as tools or consume external MCP services
+
+### Configuration
+
+All settings are managed via `MLConfig` in `.env`:
+
+```env
+# Model Configuration
+llm_model_name=gpt-4o
+llm_temperature=0.0
+embed_model_name=text-embedding-3-small
+
+# Chunking Parameters
+embed_max_depth=2
+embed_max_chunks=10
+embed_max_tokens_per_chunk=800
+
+# Retrieval Settings
+retriever_default_k=8
+```
+
+## Development
+
+### Setup
+
+```bash
+# Install dependencies
+pip install --upgrade uv hatch==1.14.2
+hatch env create
+hatch run sync
+```
+
+### Testing
+
+```bash
+# Run all tests with coverage
+hatch run cov
+
+# Run specific tests
+hatch run test tests/test_openai_model.py
+
+# Watch mode
+pytest tests/ -v
+```
+
+### Code Quality
+
+```bash
+# Run all checks (style + typing)
+hatch run all
+
+# Format code
+hatch run fmt
+
+# Type checking
+hatch run typing
+```
+
+### AMSDAL CLI
+
+```bash
+# Generate a new model
+amsdal generate model MyModel --format py
+
+# Generate property
+amsdal generate property --model MyModel embedding_field
+
+# Generate transaction
+amsdal generate transaction ProcessEmbeddings
+
+# Generate hook
+amsdal generate hook --model MyModel on_create
+```
+
+## MCP Server
+
+Run the retriever as an MCP server for integration with Claude Desktop or other MCP clients:
+
+```bash
+python -m amsdal_ml.mcp_server.server_retriever_stdio \
+  --amsdal-config "$(echo '{"async_mode": true, ...}' | base64)"
+```
+
+The server exposes a `search` tool for semantic search in your knowledge base.
+
+## License
+
+See `amsdal_ml/Third-Party Materials - AMSDAL Dependencies - License Notices.md` for dependency licenses.
+
+## Links
+
+- [AMSDAL Framework](https://github.com/amsdal/amsdal)
+- [Documentation](https://docs.amsdal.com)
+- [Issue Tracker](https://github.com/amsdal/amsdal_ml/issues)

amsdal_ml-0.2.0.dist-info/RECORD

@@ -0,0 +1,72 @@
+amsdal_ml/Third-Party Materials - AMSDAL Dependencies - License Notices.md,sha256=ML7PqsHrTMNNZn8E_rA-LzDCAafMSxMcrmSg8YOi-wo,113896
+amsdal_ml/__about__.py,sha256=FVHPBGkfhbQDi_z3v0PiKJrXXqXOx0vGW_1VaqNJi7U,22
+amsdal_ml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+amsdal_ml/app.py,sha256=K_lUz37_FUQmPwzDakDhVXA_D2SL9z1JtcuHfuBvlKE,184
+amsdal_ml/ml_config.py,sha256=UONMVG2RbKVbaYF-GdlhRQbm8flp52GxBzfqdzuLZ5w,1788
+amsdal_ml/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+amsdal_ml/agents/__init__.py,sha256=uKqtPo0Q0qeaDdz0J39XbqKDTCpT4nvm6uBWj7odxEE,393
+amsdal_ml/agents/agent.py,sha256=Yz0i5xvblv4yfXRChRMjkpTxBNQIefEw3OVsJdozpvM,1498
+amsdal_ml/agents/default_qa_agent.py,sha256=1b4GjE2-LFGow2ab4cb-K4kutv63-0Wf7svvJRWfk5I,13354
+amsdal_ml/agents/functional_calling_agent.py,sha256=4qd_-Q457XhJq0GHIXWiQwiw4WZE4LEw1o88VQ4ppsk,9166
+amsdal_ml/agents/mcp_client_tool.py,sha256=Q_AJaXqZfG9Sqs8oHMhGJV-j_-cmp-qPNuqhbhExVsg,1246
+amsdal_ml/agents/python_tool.py,sha256=qrWOfc9pz1mAU506A-0bgwhkahaNT_t_E7RmSo2slFg,2616
+amsdal_ml/agents/retriever_tool.py,sha256=ckSVPahfYQ12E3F5ouPV085LeQinlyxEQrBpRSfJzbU,2220
+amsdal_ml/agents/tool_adapters.py,sha256=GJoAx6rRnf-db_5ExPi5KpbiROF0TetcOAh8-sT1Nf0,3244
+amsdal_ml/fileio/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+amsdal_ml/fileio/base_loader.py,sha256=Ca0_zrRqj9DYSidcbcJAhkZLT_TalYnYhGRoR_RfetA,1868
+amsdal_ml/fileio/openai_loader.py,sha256=Bfe2pfkodggsslU5csg2AKRhwcoxsfpPIhFWSvMKvKY,2560
+amsdal_ml/mcp_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+amsdal_ml/mcp_client/base.py,sha256=PifmlAxxlpFkFLLN8VHKV3XbeSXKA4jcE_u4gPacm9U,497
+amsdal_ml/mcp_client/http_client.py,sha256=VFTNZ8b9sboa67_4db0K1R6CtwM6KdVjmH1t_l0FZMk,1765
+amsdal_ml/mcp_client/stdio_client.py,sha256=HTutdoLSIPu18_le_B2zcZ4qep99y6DHg7LNNA7To_s,5896
+amsdal_ml/mcp_server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+amsdal_ml/mcp_server/server_retriever_stdio.py,sha256=7PcfUShO3STNfKijs0s_aeCn7BExawaBe5wV_EEfW7Q,1741
+amsdal_ml/migrations/0000_initial.py,sha256=UeEtqHrCgmTQyGnyV2jC7yt9Ce7Xm0-MyhOQU3rRrs8,1633
+amsdal_ml/ml_ingesting/__init__.py,sha256=r1XwbdBgOvmn2QujJJaHgtKBJqqgUrb3Jvd2RFhYcJU,1069
+amsdal_ml/ml_ingesting/default_ingesting.py,sha256=PLxNZv-cEta4GWby6U2_kx8LS1D_gzIeerDVTtIol8g,12845
+amsdal_ml/ml_ingesting/embedding_data.py,sha256=6Umr2guR1fXhhwFUfKpOnzH4ex3bbaKXqg1CMlwMZeM,466
+amsdal_ml/ml_ingesting/ingesting.py,sha256=h-GdNCtutO8C75jbLko40CMjHym9Xk_nlMdNYLfBs58,1458
+amsdal_ml/ml_ingesting/model_ingester.py,sha256=XifIX9-3dWkx9i7pG2eoq9rjRKX0jUM9ni57ICgEOcs,10752
+amsdal_ml/ml_ingesting/openai_ingesting.py,sha256=_2dU2id2a3xR_y0GvZc5LUDw3_wI-wbhEFogEOKF-H0,1421
+amsdal_ml/ml_ingesting/pipeline.py,sha256=lsmgRs0bUiuDh3YLk_G4TyCZvYFOTxha6u00puaCwAQ,4968
+amsdal_ml/ml_ingesting/pipeline_interface.py,sha256=6dtVEEvfeQ4-wdhFr7RxBgzHm1I-dmxbdr6aw0t11LQ,731
+amsdal_ml/ml_ingesting/types.py,sha256=iJW8tdQ37LiIFKXhE4fvaDPXkbSHL2GV43c3kwNGakc,1602
+amsdal_ml/ml_ingesting/embedders/__init__.py,sha256=flx9X7KbLQhvoa8qhLtQqr6wt_BQ1p4OpqAd0Olmkg8,181
+amsdal_ml/ml_ingesting/embedders/embedder.py,sha256=I8J4R0uBcP8x8u04ELqWfV4r1z93FXoXJth1nP9tnwo,260
+amsdal_ml/ml_ingesting/embedders/openai_embedder.py,sha256=HKZ7N6PsMGYDEh0FJYpNgpmqlrjdnudhHyKPbSMRHs0,1133
+amsdal_ml/ml_ingesting/loaders/__init__.py,sha256=B7Gcc_URThz4FjmOc0IUEi8q4la8p1AreA5mH2Qsw9k,334
+amsdal_ml/ml_ingesting/loaders/folder_loader.py,sha256=via8ND-rL4SmGmaeQUn4z5ctRXbfwvyPtcHh3tQzWiU,2002
+amsdal_ml/ml_ingesting/loaders/loader.py,sha256=ETSdwQHtnhpXXEIawOvXahA9pwVTyxzFAJgudqRev1s,610
+amsdal_ml/ml_ingesting/loaders/pdf_loader.py,sha256=Kq1nRJHjt9PiQadF92kyC7w2WeFfFMtZI89Co-5WR9Y,4201
+amsdal_ml/ml_ingesting/loaders/text_loader.py,sha256=dOWk-sPquoh1TTRZR_jKw8X7BGKyeTUoih0ImUBRBcs,1369
+amsdal_ml/ml_ingesting/processors/__init__.py,sha256=cDWOIqjLwgIRpysJLishZl68jpAwDe4tPZyhLaPadiQ,171
+amsdal_ml/ml_ingesting/processors/cleaner.py,sha256=1hWxYTFpWckzqISewUoKTnhlhPVvPyGL1H1o7OGxX-Y,342
+amsdal_ml/ml_ingesting/processors/text_cleaner.py,sha256=sVAlTlpH0WlklXbHx53GdGA8gb1U4WAMtyoWuU0C-J0,1372
+amsdal_ml/ml_ingesting/splitters/__init__.py,sha256=3bRqxmAp60fhp7VLrEIpwToY7kG7yb2EPDUbvEDBCcg,178
+amsdal_ml/ml_ingesting/splitters/splitter.py,sha256=NewyPeWdMxIdZkx8QyP3B2v9wtEsR0Ra1hrd6mOE48U,396
+amsdal_ml/ml_ingesting/splitters/token_splitter.py,sha256=YY8DaSK8156pKpBjt3g2_0TPRISx_dM-Sx5LvTbwl0w,2762
+amsdal_ml/ml_ingesting/stores/__init__.py,sha256=NnwCVjmEdM5_fLKmCZEZwS2NEJgf_YT6VBcg4wUFZM0,191
+amsdal_ml/ml_ingesting/stores/embedding_data.py,sha256=zbYF8l6L4IgNpuLmtNYqxKzvd5Jr3sdcVFwe4a7QeUs,2366
+amsdal_ml/ml_ingesting/stores/store.py,sha256=WTX22e_7qCwCPNFmJYNIMwr8Ppkw7NlIri8SEweVoAw,617
+amsdal_ml/ml_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+amsdal_ml/ml_models/models.py,sha256=w_sFzDqV4L1OUaGzmODU1Y0nCXo19SBeqjvD-W0ROfU,5501
+amsdal_ml/ml_models/openai_model.py,sha256=00-qfaDFA76dAzSAj_P36-pvCKXQepXx6lNbCKnpH0I,24323
+amsdal_ml/ml_models/utils.py,sha256=fOwRC4gfmmtGIFsI0aXjvSPxEApFsxiQ3Hicx71QykU,146
+amsdal_ml/ml_retrievers/__init__.py,sha256=duWEkdfwbJN05yiJOfzKOK_xERLSxXGPUrCexZ6Ubhw,619
+amsdal_ml/ml_retrievers/adapters.py,sha256=-luzriafS_AZAp8yfINfVX6jTXuGlM9slF-f6UztveY,2983
+amsdal_ml/ml_retrievers/default_retriever.py,sha256=SNeBkfdgwsNxrgAl2lyHhDw5cIJD4hYwkH7_tfWkRUU,3541
+amsdal_ml/ml_retrievers/openai_retriever.py,sha256=uSYrKk_aJwUAyQdolg1ZGaWbB4w63TfLm_BQz9m4qtI,1970
+amsdal_ml/ml_retrievers/query_retriever.py,sha256=g0DNH4QSYPvbyi7R8rrMAFmpjmMm2QmipM4AhVGUpoY,17209
+amsdal_ml/ml_retrievers/retriever.py,sha256=Nh6kltqO1XirDJtUyi8Bl7Dm9d2lDEwh-4TwT1-cvcE,1303
+amsdal_ml/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+amsdal_ml/models/embedding_model.py,sha256=WYPkttS81T1Me39kEjrrnxXiyrfQPDBjuSV3tTWPrrI,774
+amsdal_ml/prompts/__init__.py,sha256=mnts4uN_tgbcJ4fJaS_gucxFIL0WSzvG_0yvQUQ_9NA,2185
+amsdal_ml/prompts/database_query_agent.prompt,sha256=XAdGg15LNmN8Mglzzsu9HnGAIpOThblTIFpHpR3p-Jk,1260
+amsdal_ml/prompts/functional_calling_agent_base.prompt,sha256=dvIWT_Dl5WGr1GCgRJDwmFPxFD4jsweqnnApnsO5n5k,258
+amsdal_ml/prompts/nl_query_filter.prompt,sha256=Qeh0qZd59ObAYxql3N3vSfDZc6PBnQUHD-0MIaQMbEY,15470
+amsdal_ml/prompts/react_chat.prompt,sha256=KGJNaaeutqMtYQ7PBnMCuR9RQQBHBa4VzXfQ4c0D3Js,1953
+amsdal_ml/utils/__init__.py,sha256=Q9ToZTkhPC6TiAx2qR_5Ap06cg94tvxorMfCU2v0xUQ,208
+amsdal_ml/utils/query_utils.py,sha256=DlU1FOwabPqg4CW8xEzhel7KjuCwkYPiB41WX8s7mbc,5496
+amsdal_ml-0.2.0.dist-info/METADATA,sha256=81zcR8zkC6u5XKxfMV2zaF5dAckyN_P2Q0Xr09OSvzw,8373
+amsdal_ml-0.2.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+amsdal_ml-0.2.0.dist-info/RECORD,,

{amsdal_ml-0.1.3.dist-info → amsdal_ml-0.2.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.27.0
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any

amsdal_ml/agents/promts/__init__.py

@@ -1,58 +0,0 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Any
-from typing import Final
-
-# avoid "magic numbers"
-_PARTS_EXPECTED: Final[int] = 2
-
-
-class _SafeDict(dict[str, Any]):
-    def __missing__(self, key: str) -> str:
-        return "{" + key + "}"
-
-
-@dataclass
-class Prompt:
-    name: str
-    system: str
-    user: str
-
-    def render_text(self, **kwargs: Any) -> str:
-        data = _SafeDict(**kwargs)
-        sys_txt = self.system.format_map(data)
-        usr_txt = self.user.format_map(data)
-        return f"{sys_txt}\n\n{usr_txt}".strip()
-
-    def render_messages(self, **kwargs: Any) -> list[dict[str, str]]:
-        data = _SafeDict(**kwargs)
-        return [
-            {"role": "system", "content": self.system.format_map(data)},
-            {"role": "user", "content": self.user.format_map(data)},
-        ]
-
-
-_prompt_cache: dict[str, Prompt] = {}
-
-
-def _load_file(name: str) -> Prompt:
-    base = Path(__file__).resolve().parent
-    path = base / f"{name}.prompt"
-    if not path.exists():
-        msg = f"Prompt '{name}' not found at {path}"
-        raise FileNotFoundError(msg)
-    raw = path.read_text(encoding="utf-8")
-    parts = raw.split("\n---\n", 1)
-    if len(parts) == _PARTS_EXPECTED:
-        system, user = parts
-    else:
-        system, user = raw, "{input}"
-    return Prompt(name=name, system=system.strip(), user=user.strip())
-
-
-def get_prompt(name: str) -> Prompt:
-    if name not in _prompt_cache:
-        _prompt_cache[name] = _load_file(name)
-    return _prompt_cache[name]

amsdal_ml-0.1.3.dist-info/METADATA

@@ -1,69 +0,0 @@
-Metadata-Version: 2.4
-Name: amsdal_ml
-Version: 0.1.3
-Summary: amsdal_ml plugin for AMSDAL Framework
-Requires-Python: >=3.11
-Requires-Dist: aiohttp==3.12.15
-Requires-Dist: amsdal-cli>=0.5.7
-Requires-Dist: amsdal-data>=0.5.9
-Requires-Dist: amsdal-models>=0.5.9
-Requires-Dist: amsdal-utils>=0.5.4
-Requires-Dist: amsdal>=0.5.6
-Requires-Dist: mcp>=0.1
-Requires-Dist: openai==1.100.2
-Requires-Dist: pydantic-settings==2.10.1
-Requires-Dist: pydantic==2.11.7
-Description-Content-Type: text/markdown
-
-# amsdal-ml
-
-This plugin extends the AMSDAL Framework with machine learning utilities, 
-including custom models for embeddings, properties for ML metadata, and 
-hooks for working with vector search and AI-driven features.
-
-## Plugin Structure
-
-- `src/models/` - Contains model definitions in Python format
-- `src/transactions/` - Contains transaction definitions
-- `pyproject.toml` - Plugin configuration file
-- `config.yml` - Configuration for connections
-
-## Installing this Plugin
-
-To use this plugin in an AMSDAL application:
-
-1. Copy the plugin directory to your AMSDAL application
-2. Import the models and transactions as needed
-3. Register the plugin in your application configuration
-
-## Development
-
-This plugin uses sync mode.
-
-### Adding Models
-
-```bash
-amsdal generate model ModelName --format py
-```
-
-### Adding Properties
-
-```bash
-amsdal generate property --model ModelName property_name
-```
-
-### Adding Transactions
-
-```bash
-amsdal generate transaction TransactionName
-```
-
-### Adding Hooks
-
-```bash
-amsdal generate hook --model ModelName on_create
-```
-
-## Testing
-
-Test your plugin by integrating it with an AMSDAL application and running the application's test suite.

amsdal_ml-0.1.3.dist-info/RECORD

@@ -1,39 +0,0 @@
-amsdal_ml/Third-Party Materials - AMSDAL Dependencies - License Notices.md,sha256=0A3jjw91I-NaTHXCw8IQiKUdFJgVavhgHaFX4Nag4jk,81658
-amsdal_ml/__about__.py,sha256=uZsygMXMKRw-7qhWojAjnpm8GFPXU92xW6XA8O5GwFY,22
-amsdal_ml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/app.py,sha256=K_lUz37_FUQmPwzDakDhVXA_D2SL9z1JtcuHfuBvlKE,184
-amsdal_ml/ml_config.py,sha256=UONMVG2RbKVbaYF-GdlhRQbm8flp52GxBzfqdzuLZ5w,1788
-amsdal_ml/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/agents/agent.py,sha256=L00RTIkopdGnJp_NctEtWRXAgWy1DAn7AEg0rMoXdJw,1514
-amsdal_ml/agents/default_qa_agent.py,sha256=MjrA5XYOKe5PwfSnkoeGmEnC8mP9asRHGHPHd1oPH6g,14017
-amsdal_ml/agents/retriever_tool.py,sha256=SqIGqYi_xMcm_MgLcwdMW2ALzYphkk02KBevH8n-Op0,1850
-amsdal_ml/agents/promts/__init__.py,sha256=3AKR3lrV067CO03XYFDmAKJv0x2oqSTcVeDIqNwoAu0,1571
-amsdal_ml/agents/promts/react_chat.prompt,sha256=EArdA102sSBOWchhub1QoaKws_DVpMqDflc5htBkFKI,1762
-amsdal_ml/fileio/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/fileio/base_loader.py,sha256=rFeClp-ZkSX6Ja1vz1RutlyMqYIGgR48CrtXDWXr4Ns,1866
-amsdal_ml/fileio/openai_loader.py,sha256=4YyxK5pBAnRm55et5yMu6X5OdK2kWTqpuPF1E2-oFZc,2572
-amsdal_ml/mcp_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/mcp_client/base.py,sha256=cNuHHCSSND4BkIyhQZ-1mJLPp630wTCtiCQSHnK2zmA,441
-amsdal_ml/mcp_client/http_client.py,sha256=2fFCaubp_cFeyCqN9CP7bVLTp4UIIEhJPq9BVHBf6-w,1719
-amsdal_ml/mcp_client/stdio_client.py,sha256=F5Y2yGFNDCE7Nfg_6QMCkp81Vb4uS2UQ1XnD_FTGM8U,5777
-amsdal_ml/mcp_server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/mcp_server/server_retriever_stdio.py,sha256=iUQNwWEDZE0OIS9vyTyJp_EOn4kvl9Gn0Okzcq-ymo0,1762
-amsdal_ml/migrations/0000_initial.py,sha256=UeEtqHrCgmTQyGnyV2jC7yt9Ce7Xm0-MyhOQU3rRrs8,1633
-amsdal_ml/ml_ingesting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/ml_ingesting/default_ingesting.py,sha256=udVAyUbjeCrsP9pk-VbAH689M3VmBRhOFbl9Que9oK0,12859
-amsdal_ml/ml_ingesting/embedding_data.py,sha256=ZWxhYq8mkFVC3HMM5nEiObgy62X8hLh1McaGegnRUsk,355
-amsdal_ml/ml_ingesting/ingesting.py,sha256=h-GdNCtutO8C75jbLko40CMjHym9Xk_nlMdNYLfBs58,1458
-amsdal_ml/ml_ingesting/openai_ingesting.py,sha256=_2dU2id2a3xR_y0GvZc5LUDw3_wI-wbhEFogEOKF-H0,1421
-amsdal_ml/ml_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/ml_models/models.py,sha256=gZzZrjsoAnFc5pPwqqLPNh5RYxwKKaFyNg56NJnsn4w,2286
-amsdal_ml/ml_models/openai_model.py,sha256=yQ6r4K7AOeG3NfWT6pXgjkRPMT0FuQPqFUWeHSwz0u8,14295
-amsdal_ml/ml_retrievers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/ml_retrievers/default_retriever.py,sha256=ykAzi6gESyG1693nALpPJ9XhKV_We1yrNxbYo1eG748,3233
-amsdal_ml/ml_retrievers/openai_retriever.py,sha256=oY71oPJdFuECWaJL_ByKZFE7HRJ-S6ypRzzJ7XjI7H8,1236
-amsdal_ml/ml_retrievers/retriever.py,sha256=zHvaAOAD6H4IaIaYA_wy2e8tMmGtOnyNsDS2B4dQjBU,1005
-amsdal_ml/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-amsdal_ml/models/embedding_model.py,sha256=mdMSYHrkSIKHi5mg4HqMaTTiPGqLYtRdRkbEK_trFWw,774
-amsdal_ml-0.1.3.dist-info/METADATA,sha256=BETzPNugrsUz-RL3yG-2I-4I_WBSLkJ5oRJYxyZxEDY,1676
-amsdal_ml-0.1.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-amsdal_ml-0.1.3.dist-info/RECORD,,