dewey-haystack 0.1.0__tar.gz

dewey_haystack-0.1.0/PKG-INFO

@@ -0,0 +1,199 @@
+Metadata-Version: 2.4
+Name: dewey-haystack
+Version: 0.1.0
+Summary: Haystack integration for Dewey — document store, retriever, and research component
+Author-email: Dewey <hi@meetdewey.com>
+License-Expression: MIT
+Project-URL: Homepage, https://meetdewey.com
+Project-URL: Repository, https://github.com/meetdewey/dewey-haystack
+Keywords: haystack,dewey,rag,retrieval,document-store,llm
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: meetdewey>=1.0
+Requires-Dist: haystack-ai>=2.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: pytest-mock>=3; extra == "dev"
+
+# dewey-haystack
+
+[![CI](https://github.com/meetdewey/dewey-haystack/actions/workflows/ci.yml/badge.svg)](https://github.com/meetdewey/dewey-haystack/actions/workflows/ci.yml)
+
+[Haystack](https://haystack.deepset.ai/) integration for [Dewey](https://meetdewey.com) — document store, retriever, and research component.
+
+## Installation
+
+```bash
+pip install dewey-haystack
+```
+
+## Components
+
+### DeweyDocumentStore
+
+Haystack DocumentStore backed by a Dewey collection. Handles document upload and deletion; Dewey manages chunking and embeddings automatically.
+
+```python
+from haystack_integrations.document_stores.dewey import DeweyDocumentStore
+from haystack.utils import Secret
+
+store = DeweyDocumentStore(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+)
+```
+
+Upload Haystack Documents:
+
+```python
+from haystack import Document
+
+store.write_documents([
+    Document(content="Neural networks learn via backpropagation.", meta={"source": "ml.txt"}),
+    Document(content="Transformers use self-attention mechanisms."),
+])
+```
+
+### DeweyRetriever
+
+Drop-in Haystack retriever backed by Dewey's hybrid semantic + BM25 search.
+
+```python
+from haystack import Pipeline
+from haystack_integrations.document_stores.dewey import DeweyDocumentStore
+from haystack_integrations.components.retrievers.dewey import DeweyRetriever
+from haystack.utils import Secret
+
+store = DeweyDocumentStore(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+)
+
+pipeline = Pipeline()
+pipeline.add_component("retriever", DeweyRetriever(document_store=store, top_k=8))
+
+result = pipeline.run({"retriever": {"query": "What are the key findings?"}})
+for doc in result["retriever"]["documents"]:
+    print(f"[{doc.meta['filename']}] {doc.content}")
+```
+
+Each returned `Document` carries citation metadata:
+
+| Field | Description |
+|---|---|
+| `score` | Relevance score (0–1) |
+| `document_id` | Dewey document ID |
+| `filename` | Original filename |
+| `section_id` | Section ID |
+| `section_title` | Section heading |
+| `section_level` | Heading depth (1 = top-level) |
+
+**RAG pipeline with an LLM:**
+
+```python
+from haystack.components.builders import PromptBuilder
+from haystack.components.generators import OpenAIGenerator
+
+prompt_template = """
+Answer the question using only the provided context.
+
+Context:
+{% for doc in documents %}
+- {{ doc.content }}
+{% endfor %}
+
+Question: {{ query }}
+"""
+
+pipeline = Pipeline()
+pipeline.add_component("retriever", DeweyRetriever(document_store=store, top_k=5))
+pipeline.add_component("prompt", PromptBuilder(template=prompt_template))
+pipeline.add_component("llm", OpenAIGenerator(model="gpt-4o-mini"))
+
+pipeline.connect("retriever.documents", "prompt.documents")
+pipeline.connect("prompt.prompt", "llm.prompt")
+
+result = pipeline.run({
+    "retriever": {"query": "What were the main findings?"},
+    "prompt": {"query": "What were the main findings?"},
+})
+print(result["llm"]["replies"][0])
+```
+
+### DeweyResearchComponent
+
+A Haystack component that runs Dewey's full agentic research loop — searching, reading, and synthesising across multiple documents — and returns a grounded Markdown answer with cited sources.
+
+Use this as a drop-in replacement for an LLM generator when you want Dewey to handle both retrieval *and* generation.
+
+```python
+from haystack import Pipeline
+from haystack_integrations.components.retrievers.dewey import DeweyResearchComponent
+from haystack.utils import Secret
+
+pipeline = Pipeline()
+pipeline.add_component(
+    "research",
+    DeweyResearchComponent(
+        api_key=Secret.from_env_var("DEWEY_API_KEY"),
+        collection_id="3f7a1b2c-...",
+        depth="balanced",
+    ),
+)
+
+result = pipeline.run({"research": {"query": "What were the key findings across all studies?"}})
+print(result["research"]["answer"])
+
+for source in result["research"]["sources"]:
+    print(f"  [{source.meta['filename']}] {source.content[:80]}...")
+```
+
+**Outputs:**
+
+| Key | Type | Description |
+|---|---|---|
+| `answer` | `str` | Synthesised Markdown answer |
+| `sources` | `list[Document]` | Source chunks cited by the answer |
+
+**Research depths:**
+
+| depth | Speed | Tools | Requires BYOK |
+|---|---|---|---|
+| `quick` | fast | basic search | no |
+| `balanced` | fast | basic search | no |
+| `deep` | slower | full tool suite | yes |
+| `exhaustive` | slowest | full tool suite | yes |
+
+`deep` and `exhaustive` require a Dewey Pro plan and a BYOK API key configured on your project.
+
+**With a custom model:**
+
+```python
+DeweyResearchComponent(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+    depth="deep",
+    model="claude-sonnet-4-6",  # requires Anthropic BYOK key on your project
+)
+```
+
+## Requirements
+
+- Python 3.9+
+- `meetdewey >= 1.0`
+- `haystack-ai >= 2.0`
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```

dewey_haystack-0.1.0/README.md

@@ -0,0 +1,174 @@
+# dewey-haystack
+
+[![CI](https://github.com/meetdewey/dewey-haystack/actions/workflows/ci.yml/badge.svg)](https://github.com/meetdewey/dewey-haystack/actions/workflows/ci.yml)
+
+[Haystack](https://haystack.deepset.ai/) integration for [Dewey](https://meetdewey.com) — document store, retriever, and research component.
+
+## Installation
+
+```bash
+pip install dewey-haystack
+```
+
+## Components
+
+### DeweyDocumentStore
+
+Haystack DocumentStore backed by a Dewey collection. Handles document upload and deletion; Dewey manages chunking and embeddings automatically.
+
+```python
+from haystack_integrations.document_stores.dewey import DeweyDocumentStore
+from haystack.utils import Secret
+
+store = DeweyDocumentStore(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+)
+```
+
+Upload Haystack Documents:
+
+```python
+from haystack import Document
+
+store.write_documents([
+    Document(content="Neural networks learn via backpropagation.", meta={"source": "ml.txt"}),
+    Document(content="Transformers use self-attention mechanisms."),
+])
+```
+
+### DeweyRetriever
+
+Drop-in Haystack retriever backed by Dewey's hybrid semantic + BM25 search.
+
+```python
+from haystack import Pipeline
+from haystack_integrations.document_stores.dewey import DeweyDocumentStore
+from haystack_integrations.components.retrievers.dewey import DeweyRetriever
+from haystack.utils import Secret
+
+store = DeweyDocumentStore(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+)
+
+pipeline = Pipeline()
+pipeline.add_component("retriever", DeweyRetriever(document_store=store, top_k=8))
+
+result = pipeline.run({"retriever": {"query": "What are the key findings?"}})
+for doc in result["retriever"]["documents"]:
+    print(f"[{doc.meta['filename']}] {doc.content}")
+```
+
+Each returned `Document` carries citation metadata:
+
+| Field | Description |
+|---|---|
+| `score` | Relevance score (0–1) |
+| `document_id` | Dewey document ID |
+| `filename` | Original filename |
+| `section_id` | Section ID |
+| `section_title` | Section heading |
+| `section_level` | Heading depth (1 = top-level) |
+
+**RAG pipeline with an LLM:**
+
+```python
+from haystack.components.builders import PromptBuilder
+from haystack.components.generators import OpenAIGenerator
+
+prompt_template = """
+Answer the question using only the provided context.
+
+Context:
+{% for doc in documents %}
+- {{ doc.content }}
+{% endfor %}
+
+Question: {{ query }}
+"""
+
+pipeline = Pipeline()
+pipeline.add_component("retriever", DeweyRetriever(document_store=store, top_k=5))
+pipeline.add_component("prompt", PromptBuilder(template=prompt_template))
+pipeline.add_component("llm", OpenAIGenerator(model="gpt-4o-mini"))
+
+pipeline.connect("retriever.documents", "prompt.documents")
+pipeline.connect("prompt.prompt", "llm.prompt")
+
+result = pipeline.run({
+    "retriever": {"query": "What were the main findings?"},
+    "prompt": {"query": "What were the main findings?"},
+})
+print(result["llm"]["replies"][0])
+```
+
+### DeweyResearchComponent
+
+A Haystack component that runs Dewey's full agentic research loop — searching, reading, and synthesising across multiple documents — and returns a grounded Markdown answer with cited sources.
+
+Use this as a drop-in replacement for an LLM generator when you want Dewey to handle both retrieval *and* generation.
+
+```python
+from haystack import Pipeline
+from haystack_integrations.components.retrievers.dewey import DeweyResearchComponent
+from haystack.utils import Secret
+
+pipeline = Pipeline()
+pipeline.add_component(
+    "research",
+    DeweyResearchComponent(
+        api_key=Secret.from_env_var("DEWEY_API_KEY"),
+        collection_id="3f7a1b2c-...",
+        depth="balanced",
+    ),
+)
+
+result = pipeline.run({"research": {"query": "What were the key findings across all studies?"}})
+print(result["research"]["answer"])
+
+for source in result["research"]["sources"]:
+    print(f"  [{source.meta['filename']}] {source.content[:80]}...")
+```
+
+**Outputs:**
+
+| Key | Type | Description |
+|---|---|---|
+| `answer` | `str` | Synthesised Markdown answer |
+| `sources` | `list[Document]` | Source chunks cited by the answer |
+
+**Research depths:**
+
+| depth | Speed | Tools | Requires BYOK |
+|---|---|---|---|
+| `quick` | fast | basic search | no |
+| `balanced` | fast | basic search | no |
+| `deep` | slower | full tool suite | yes |
+| `exhaustive` | slowest | full tool suite | yes |
+
+`deep` and `exhaustive` require a Dewey Pro plan and a BYOK API key configured on your project.
+
+**With a custom model:**
+
+```python
+DeweyResearchComponent(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+    depth="deep",
+    model="claude-sonnet-4-6",  # requires Anthropic BYOK key on your project
+)
+```
+
+## Requirements
+
+- Python 3.9+
+- `meetdewey >= 1.0`
+- `haystack-ai >= 2.0`
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```

dewey_haystack-0.1.0/pyproject.toml

@@ -0,0 +1,41 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "dewey-haystack"
+version = "0.1.0"
+description = "Haystack integration for Dewey — document store, retriever, and research component"
+readme = "README.md"
+requires-python = ">=3.9"
+license = "MIT"
+authors = [{ name = "Dewey", email = "hi@meetdewey.com" }]
+keywords = ["haystack", "dewey", "rag", "retrieval", "document-store", "llm"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "meetdewey>=1.0",
+    "haystack-ai>=2.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7",
+    "pytest-mock>=3",
+]
+
+[project.urls]
+Homepage = "https://meetdewey.com"
+Repository = "https://github.com/meetdewey/dewey-haystack"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["haystack_integrations*"]

dewey_haystack-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

dewey_haystack-0.1.0/src/dewey_haystack.egg-info/PKG-INFO

@@ -0,0 +1,199 @@
+Metadata-Version: 2.4
+Name: dewey-haystack
+Version: 0.1.0
+Summary: Haystack integration for Dewey — document store, retriever, and research component
+Author-email: Dewey <hi@meetdewey.com>
+License-Expression: MIT
+Project-URL: Homepage, https://meetdewey.com
+Project-URL: Repository, https://github.com/meetdewey/dewey-haystack
+Keywords: haystack,dewey,rag,retrieval,document-store,llm
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: meetdewey>=1.0
+Requires-Dist: haystack-ai>=2.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: pytest-mock>=3; extra == "dev"
+
+# dewey-haystack
+
+[![CI](https://github.com/meetdewey/dewey-haystack/actions/workflows/ci.yml/badge.svg)](https://github.com/meetdewey/dewey-haystack/actions/workflows/ci.yml)
+
+[Haystack](https://haystack.deepset.ai/) integration for [Dewey](https://meetdewey.com) — document store, retriever, and research component.
+
+## Installation
+
+```bash
+pip install dewey-haystack
+```
+
+## Components
+
+### DeweyDocumentStore
+
+Haystack DocumentStore backed by a Dewey collection. Handles document upload and deletion; Dewey manages chunking and embeddings automatically.
+
+```python
+from haystack_integrations.document_stores.dewey import DeweyDocumentStore
+from haystack.utils import Secret
+
+store = DeweyDocumentStore(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+)
+```
+
+Upload Haystack Documents:
+
+```python
+from haystack import Document
+
+store.write_documents([
+    Document(content="Neural networks learn via backpropagation.", meta={"source": "ml.txt"}),
+    Document(content="Transformers use self-attention mechanisms."),
+])
+```
+
+### DeweyRetriever
+
+Drop-in Haystack retriever backed by Dewey's hybrid semantic + BM25 search.
+
+```python
+from haystack import Pipeline
+from haystack_integrations.document_stores.dewey import DeweyDocumentStore
+from haystack_integrations.components.retrievers.dewey import DeweyRetriever
+from haystack.utils import Secret
+
+store = DeweyDocumentStore(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+)
+
+pipeline = Pipeline()
+pipeline.add_component("retriever", DeweyRetriever(document_store=store, top_k=8))
+
+result = pipeline.run({"retriever": {"query": "What are the key findings?"}})
+for doc in result["retriever"]["documents"]:
+    print(f"[{doc.meta['filename']}] {doc.content}")
+```
+
+Each returned `Document` carries citation metadata:
+
+| Field | Description |
+|---|---|
+| `score` | Relevance score (0–1) |
+| `document_id` | Dewey document ID |
+| `filename` | Original filename |
+| `section_id` | Section ID |
+| `section_title` | Section heading |
+| `section_level` | Heading depth (1 = top-level) |
+
+**RAG pipeline with an LLM:**
+
+```python
+from haystack.components.builders import PromptBuilder
+from haystack.components.generators import OpenAIGenerator
+
+prompt_template = """
+Answer the question using only the provided context.
+
+Context:
+{% for doc in documents %}
+- {{ doc.content }}
+{% endfor %}
+
+Question: {{ query }}
+"""
+
+pipeline = Pipeline()
+pipeline.add_component("retriever", DeweyRetriever(document_store=store, top_k=5))
+pipeline.add_component("prompt", PromptBuilder(template=prompt_template))
+pipeline.add_component("llm", OpenAIGenerator(model="gpt-4o-mini"))
+
+pipeline.connect("retriever.documents", "prompt.documents")
+pipeline.connect("prompt.prompt", "llm.prompt")
+
+result = pipeline.run({
+    "retriever": {"query": "What were the main findings?"},
+    "prompt": {"query": "What were the main findings?"},
+})
+print(result["llm"]["replies"][0])
+```
+
+### DeweyResearchComponent
+
+A Haystack component that runs Dewey's full agentic research loop — searching, reading, and synthesising across multiple documents — and returns a grounded Markdown answer with cited sources.
+
+Use this as a drop-in replacement for an LLM generator when you want Dewey to handle both retrieval *and* generation.
+
+```python
+from haystack import Pipeline
+from haystack_integrations.components.retrievers.dewey import DeweyResearchComponent
+from haystack.utils import Secret
+
+pipeline = Pipeline()
+pipeline.add_component(
+    "research",
+    DeweyResearchComponent(
+        api_key=Secret.from_env_var("DEWEY_API_KEY"),
+        collection_id="3f7a1b2c-...",
+        depth="balanced",
+    ),
+)
+
+result = pipeline.run({"research": {"query": "What were the key findings across all studies?"}})
+print(result["research"]["answer"])
+
+for source in result["research"]["sources"]:
+    print(f"  [{source.meta['filename']}] {source.content[:80]}...")
+```
+
+**Outputs:**
+
+| Key | Type | Description |
+|---|---|---|
+| `answer` | `str` | Synthesised Markdown answer |
+| `sources` | `list[Document]` | Source chunks cited by the answer |
+
+**Research depths:**
+
+| depth | Speed | Tools | Requires BYOK |
+|---|---|---|---|
+| `quick` | fast | basic search | no |
+| `balanced` | fast | basic search | no |
+| `deep` | slower | full tool suite | yes |
+| `exhaustive` | slowest | full tool suite | yes |
+
+`deep` and `exhaustive` require a Dewey Pro plan and a BYOK API key configured on your project.
+
+**With a custom model:**
+
+```python
+DeweyResearchComponent(
+    api_key=Secret.from_env_var("DEWEY_API_KEY"),
+    collection_id="3f7a1b2c-...",
+    depth="deep",
+    model="claude-sonnet-4-6",  # requires Anthropic BYOK key on your project
+)
+```
+
+## Requirements
+
+- Python 3.9+
+- `meetdewey >= 1.0`
+- `haystack-ai >= 2.0`
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```

dewey_haystack-0.1.0/src/dewey_haystack.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+README.md
+pyproject.toml
+src/dewey_haystack.egg-info/PKG-INFO
+src/dewey_haystack.egg-info/SOURCES.txt
+src/dewey_haystack.egg-info/dependency_links.txt
+src/dewey_haystack.egg-info/requires.txt
+src/dewey_haystack.egg-info/top_level.txt
+src/haystack_integrations/components/retrievers/dewey/__init__.py
+src/haystack_integrations/components/retrievers/dewey/dewey_research_component.py
+src/haystack_integrations/components/retrievers/dewey/dewey_retriever.py
+src/haystack_integrations/document_stores/dewey/__init__.py
+src/haystack_integrations/document_stores/dewey/dewey_document_store.py
+tests/test_document_store.py
+tests/test_research_component.py
+tests/test_retriever.py

dewey_haystack-0.1.0/src/dewey_haystack.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dewey_haystack-0.1.0/src/dewey_haystack.egg-info/requires.txt

@@ -0,0 +1,6 @@
+meetdewey>=1.0
+haystack-ai>=2.0
+
+[dev]
+pytest>=7
+pytest-mock>=3

dewey_haystack-0.1.0/src/dewey_haystack.egg-info/top_level.txt

@@ -0,0 +1 @@
+haystack_integrations

dewey_haystack-0.1.0/src/haystack_integrations/components/retrievers/dewey/__init__.py

@@ -0,0 +1,8 @@
+from haystack_integrations.components.retrievers.dewey.dewey_research_component import (
+    DeweyResearchComponent,
+)
+from haystack_integrations.components.retrievers.dewey.dewey_retriever import (
+    DeweyRetriever,
+)
+
+__all__ = ["DeweyRetriever", "DeweyResearchComponent"]