docs: dsRAG integration

qdrant-landing/content/documentation/frameworks/_index.md

@@ -14,6 +14,7 @@ partition: build
 | [CrewAI](/documentation/frameworks/crewai/)                   | CrewAI is a framework to build automated workflows using multiple AI agents that perform complex tasks.              |
 | [DocArray](/documentation/frameworks/docarray/)               | Python library for managing data in multi-modal AI applications.                                                     |
 | [DSPy](/documentation/frameworks/dspy/)                       | Framework for algorithmically optimizing LM prompts and weights.                                                     |
+| [dsRAG](/documentation/frameworks/dsrag/)                     | High-performance Python retrieval engine for unstructured data.                                                      |
 | [Feast](/documentation/frameworks/feast/)                     | Open-source feature store to operate production ML systems at scale as a set of features.                            |
 | [Fifty-One](/documentation/frameworks/fifty-one/)             | Toolkit for building high-quality datasets and computer vision models.                                               |
 | [Genkit](/documentation/frameworks/genkit/)                   | Framework to build, deploy, and monitor production-ready AI-powered apps.                                            |

qdrant-landing/content/documentation/frameworks/dsrag.md

@@ -0,0 +1,50 @@
+---
+title: dsRAG
+---
+
+# dsRAG
+
+[dsRAG](https://github.com/D-Star-AI/dsRAG) is a retrieval engine for unstructured data. It is especially good at handling challenging queries over dense text, like financial reports, legal documents, and academic papers. dsRAG achieves substantially higher accuracy than vanilla RAG baselines on complex open-book question answering tasks
+
+You can use the Qdrant connector in dsRAG to add and semantically retrieve documents from your collections.
+
+## Usage Example
+
+```python
+from dsrag.database.vector import QdrantVectorDB
+import numpy as np
+from qdrant_clien import models
+
+db = QdrantVectorDB(kb_id=self.kb_id, url="http://localhost:6334", prefer_grpc=True)
+vectors = [np.array([1, 0]), np.array([0, 1])]
+
+# You can use any document loaders available with dsRAG
+# We'll use literals for demonstration
+documents = [
+    {
+        "doc_id": "1",
+        "chunk_index": 0,
+        "chunk_header": "Header1",
+        "chunk_text": "Text1",
+    },
+    {
+        "doc_id": "2",
+        "chunk_index": 1,
+        "chunk_header": "Header2",
+        "chunk_text": "Text2",
+    },
+]
+
+db.add_vectors(vectors, documents)
+
+metadata_filter = models.Filter(
+    must=[models.FieldCondition(key="doc_id", match=models.MatchValue(value="1"))]
+)
+
+db.search(query_vector, top_k=4, metadata_filter=metadata_filter)
+```
+
+## Further Reading
+
+- [dsRAG Source](https://github.com/D-Star-AI/dsRAG).
+- [dsRAG Examples](https://github.com/D-Star-AI/dsRAG/tree/main/examples)