Metadata-Version: 2.4
Name: traceAI-weaviate
Version: 0.1.1
Summary: OpenTelemetry instrumentation for Weaviate vector database
License: Apache-2.0
Keywords: opentelemetry,weaviate,vector-database,tracing,observability,rag,traceai,futureagi,llm
Author: Future AGI
Author-email: no-reply@futureagi.com
Requires-Python: >3.9,<3.14
Classifier: Framework :: OpenTelemetry
Classifier: Framework :: OpenTelemetry :: Instrumentations
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: System :: Monitoring
Requires-Dist: fi-instrumentation-otel (>=0.1.11)
Requires-Dist: weaviate-client (>=4.0.0)
Requires-Dist: wrapt (>=1.0.0)
Project-URL: Changelog, https://github.com/future-agi/traceAI/blob/dev/python/frameworks/weaviate/CHANGELOG.md
Project-URL: Documentation, https://docs.futureagi.com/docs/tracing
Project-URL: Homepage, https://futureagi.com
Project-URL: Issues, https://github.com/future-agi/traceAI/issues
Project-URL: Repository, https://github.com/future-agi/traceAI/tree/dev/python/frameworks/weaviate
Description-Content-Type: text/markdown

# traceAI-weaviate

OpenTelemetry instrumentation for [Weaviate](https://weaviate.io/) vector database (v4 API).

## Installation

```bash
pip install traceAI-weaviate
```

## Quick Start

```python
from fi_instrumentation import register
from traceai_weaviate import WeaviateInstrumentor
import weaviate

trace_provider = register(project_name="my-rag-app")
WeaviateInstrumentor().instrument(tracer_provider=trace_provider)

client = weaviate.connect_to_local()
collection = client.collections.get("Documents")

# All operations are traced
results = collection.query.near_text(query="machine learning", limit=5)
collection.data.insert(properties={"title": "My Doc", "content": "..."})
```

## Instrumented Operations

| Operation | Span Name | Description |
|-----------|-----------|-------------|
| `near_vector` | `weaviate near_vector` | Vector similarity search |
| `near_text` | `weaviate near_text` | Text-based semantic search |
| `hybrid` | `weaviate hybrid` | Hybrid BM25 + vector search |
| `bm25` | `weaviate bm25` | Keyword search |
| `fetch_objects` | `weaviate fetch_objects` | Fetch objects |
| `insert` | `weaviate insert` | Insert single object |
| `insert_many` | `weaviate insert_many` | Batch insert |
| `delete_by_id` | `weaviate delete_by_id` | Delete by ID |
| `delete_many` | `weaviate delete_many` | Batch delete |

## License

Apache License 2.0

