NekoPunch
f5dfb1413e
* feat(python): add Mistral chat client Implements native Mistral support (#7366) with streaming, tool calling, and structured output. Talks to the REST API directly over httpx: the mistralai SDK's pinned OpenTelemetry deps conflict with the workspace. * refactor(python): simplify Mistral client per review Drop the streamed tool-call accumulator and multi-choice parsing in favor of the framework's built-in fragment merging, mark n unsupported, omit unset strict from json_schema, and leave CI secret wiring to maintainers. * test(python): drop n forwarding assertion n is typed as unsupported on MistralChatOptions; the option-mapping test still passed n, failing pyrefly/ty/zuban/mypy in CI. * refactor(python): drop n from MistralChatOptions n is not part of the base ChatOptions, so removing the key rejects it without an explicit None override. * feat(python): mark Mistral feature usage Both clients flip the shared FeatureIndex.MISTRAL bit before each request, matching the feature-usage telemetry other providers emit. * fix(python): key streamed tool calls by index Mistral omits the tool call id on continuation fragments, and the framework only coalesces empty-id fragments into the immediately preceding call, so interleaved parallel calls merged into the wrong call with corrupted arguments. Accumulate fragments per (choice, index) and emit each call only once complete. * fix(python): restore Mistral SDK client injection Dropping the mistralai dependency turned the embedding client's client= parameter into a breaking change for injected SDK clients. Add http_client= for httpx.AsyncClient and keep client= working: httpx goes to the REST path, a duck-typed mistralai.Mistral goes through the legacy SDK path with a DeprecationWarning until the next major release. * chore(python): tidy Mistral sample header
1.7 KiB
1.7 KiB
Mistral Package (agent-framework-mistral)
Integration with Mistral AI for chat completions and embedding generation.
Implementation Notes
- Talks to the Mistral REST API directly over
httpx; the officialmistralaiSDK is not used because its pinned OpenTelemetry requirements conflict with the rest of the framework.
Main Classes
MistralChatClient- Chat client for Mistral AI models with function invocation, middleware, and telemetryRawMistralChatClient- Chat client without the batteries-included layersMistralChatOptions- Options TypedDict for Mistral-specific chat parametersMistralSettings- TypedDict settings for Mistral chat configurationMistralEmbeddingClient- Embedding client for Mistral AI modelsMistralEmbeddingOptions- Options TypedDict for Mistral-specific embedding parametersMistralEmbeddingSettings- TypedDict settings for Mistral configuration
Usage
from agent_framework import Agent
from agent_framework.mistral import MistralChatClient
# Requires MISTRAL_API_KEY environment variable (or pass api_key= directly)
client = MistralChatClient(model="mistral-large-latest")
try:
agent = Agent(client=client)
result = await agent.run("Hello!")
finally:
await client.close()
from agent_framework.mistral import MistralEmbeddingClient
# Requires MISTRAL_API_KEY environment variable (or pass api_key= directly)
client = MistralEmbeddingClient(model="mistral-embed")
try:
result = await client.get_embeddings(["Hello, world!"])
print(result[0].vector)
finally:
await client.close()
Import Path
from agent_framework.mistral import MistralChatClient, MistralEmbeddingClient