agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: Add Mistral AI embedding client package (#5480)

Browse Source 
* Python: Add Mistral AI embedding client package

Signed-off-by: Daria Korenieva <daric2612@gmail.com>

* Address review feedback: fix dimensions check, sort embeddings by index, align docs

Signed-off-by: Daria Korenieva <daric2612@gmail.com>

* Address review feedback: downgrade to alpha, remove integration tests - Change version to 1.0.0a260505 (alpha) - Update classifier to Development Status :: 3 - Alpha - Update PACKAGE_STATUS.md to alpha - Remove Mistral from integration test workflows (no API keys yet)

Signed-off-by: Daria Korenieva <daric2612@gmail.com>

* Add samples directory for alpha package compliance Per python-package-management skill: alpha packages must include samples inside the package directory.

Signed-off-by: Daria Korenieva <daric2612@gmail.com>

* Fix ruff formatting in sample file

Signed-off-by: Daria Korenieva <daric2612@gmail.com>

---------

Signed-off-by: Daria Korenieva <daric2612@gmail.com>
This commit is contained in:
Daria Korenieva
2026-05-29 00:20:56 -07:00
committed by GitHub
Unverified
parent 1fccf16f11
commit d2d5384f28
15 changed files with 2473 additions and 1710 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/packages/mistral/README.md
+42
View File
@@ -0,0 +1,42 @@
# Get Started with Microsoft Agent Framework Mistral AI
Please install this package:
```bash
pip install agent-framework-mistral --pre
```
and see the [README](https://github.com/microsoft/agent-framework/tree/main/python/README.md) for more information.
## Embedding Client
The `MistralEmbeddingClient` provides embedding generation using Mistral AI models.
### Quick Start
```python
from agent_framework_mistral import MistralEmbeddingClient
# Using environment variables (MISTRAL_API_KEY, MISTRAL_EMBEDDING_MODEL)
client = MistralEmbeddingClient()
# Or passing parameters directly
client = MistralEmbeddingClient(
model="mistral-embed",
api_key="your-api-key",
)
# Generate embeddings
result = await client.get_embeddings(["Hello, world!", "How are you?"])
for embedding in result:
print(f"Dimensions: {embedding.dimensions}")
print(f"Vector: {embedding.vector[:5]}...")
```
### Configuration
| Environment Variable | Description |
|---|---|
| `MISTRAL_API_KEY` | Your Mistral AI API key |
| `MISTRAL_EMBEDDING_MODEL` | Embedding model name (e.g., `mistral-embed`) |
| `MISTRAL_SERVER_URL` | Optional server URL override |