mistralai 1.0.0rc1__py3-none-any.whl → 1.0.0rc2__py3-none-any.whl

{mistralai-1.0.0rc1.dist-info → mistralai-1.0.0rc2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mistralai
-Version: 1.0.0rc1
+Version: 1.0.0rc2
 Summary: Python Client SDK for the Mistral AI API.
 Author: Mistral
 Requires-Python: >=3.8,<4.0
@@ -61,12 +61,12 @@ s = Mistral(
 )
 
 
-res = s.chat.create(messages=[
+res = s.chat.complete(model="mistral-small-latest", messages=[
     {
         "content": "Who is the best French painter? Answer in one short sentence.",
         "role": "user",
     },
-], model="mistral-small-latest")
+])
 
 if res is not None:
     # handle response
@@ -86,12 +86,12 @@ async def main():
     s = Mistral(
         api_key=os.getenv("MISTRAL_API_KEY", ""),
     )
-    res = await s.chat.create_async(messages=[
+    res = await s.chat.complete_async(model="mistral-small-latest", messages=[
         {
             "content": "Who is the best French painter? Answer in one short sentence.",
             "role": "user",
         },
-    ], model="mistral-small-latest")
+    ])
     if res is not None:
         # handle response
         pass
@@ -144,17 +144,72 @@ async def main():
         # handle response
         pass
 
+asyncio.run(main())
+```
+
+### Create Agents Completions
+
+This example shows how to create agents completions.
+
+```python
+# Synchronous Example
+from mistralai import Mistral
+import os
+
+s = Mistral(
+    api_key=os.getenv("MISTRAL_API_KEY", ""),
+)
+
+
+res = s.agents.complete(messages=[
+    {
+        "content": "Who is the best French painter? Answer in one short sentence.",
+        "role": "user",
+    },
+], agent_id="<value>")
+
+if res is not None:
+    # handle response
+    pass
+```
+
+</br>
+
+The same SDK client can also be used to make asychronous requests by importing asyncio.
+```python
+# Asynchronous Example
+import asyncio
+from mistralai import Mistral
+import os
+
+async def main():
+    s = Mistral(
+        api_key=os.getenv("MISTRAL_API_KEY", ""),
+    )
+    res = await s.agents.complete_async(messages=[
+        {
+            "content": "Who is the best French painter? Answer in one short sentence.",
+            "role": "user",
+        },
+    ], agent_id="<value>")
+    if res is not None:
+        # handle response
+        pass
+
 asyncio.run(main())
 ```
 <!-- End SDK Example Usage [usage] -->
 
+## Providers' SDKs Example Usage
+
 ### Azure AI
 
 **Prerequisites**
+
 Before you begin, ensure you have `AZUREAI_ENDPOINT` and an `AZURE_API_KEY`. To obtain these, you will need to deploy Mistral on Azure AI.
 See [instructions for deploying Mistral on Azure AI here](https://docs.mistral.ai/deployment/cloud/azure/).
 
-Here's a basic example to get you started. You can also run [the example in the `examples` directory](/examples/azure/).
+Here's a basic example to get you started. You can also run [the example in the `examples` directory](/examples/azure).
 
 ```python
 import asyncio
@@ -164,33 +219,32 @@ from mistralai_azure import MistralAzure
 
 client = MistralAzure(
     azure_api_key=os.getenv("AZURE_API_KEY", ""),
-    azure_endpoint="your_azure_endpoint"
+    azure_endpoint=os.getenv("AZURE_ENDPOINT", "")
 )
 
 async def main() -> None:
-    res = await client.chat.create_async(
-        request={
-            "max_tokens": 100,
-            "temperature": 0.5,
-            "messages": [
-                {
-                    "content": "Hello there!",
-                    "role": "user"
-                }
-            ]
-        }
+    res = await client.chat.complete_async( 
+        max_tokens= 100,
+        temperature= 0.5,
+        messages= [
+            {
+                "content": "Hello there!",
+                "role": "user"
+            }
+        ]
     )
     print(res)
 
 asyncio.run(main())
 ```
-The documentation for the Azure SDK is available [here](/packages/mistralai_azure/README.md).
+The documentation for the Azure SDK is available [here](packages/mistralai_azure/README.md).
 
 ### Google Cloud
 
+
 **Prerequisites**
 
-Before you begin, you will need to create a Google Cloud project and enable the Mistral API. To do this, follow the instructions [here](https://docs.mistral.ai/deployment/cloud/google/).
+Before you begin, you will need to create a Google Cloud project and enable the Mistral API. To do this, follow the instructions [here](https://docs.mistral.ai/deployment/cloud/vertex/).
 
 To run this locally you will also need to ensure you are authenticated with Google Cloud. You can do this by running
 
@@ -218,23 +272,21 @@ client = MistralGoogleCloud()
 
 
 async def main() -> None:
-    res = await client.chat.create_async(
-        request={
-            "model": "mistral-small-2402",
-            "messages": [
-                {
-                    "content": "Hello there!",
-                    "role": "user"
-                }
-            ]
-        }
+    res = await client.chat.complete_async(
+        model= "mistral-small-2402",
+        messages= [
+            {
+                "content": "Hello there!",
+                "role": "user"
+            }
+        ]
     )
     print(res)
 
 asyncio.run(main())
 ```
 
-The documentation for the GCP SDK is available [here](/packages/mistralai_gcp/README.md).
+The documentation for the GCP SDK is available [here](packages/mistralai_gcp/README.md).
 
 
 <!-- Start Available Resources and Operations [operations] -->
@@ -256,24 +308,30 @@ The documentation for the GCP SDK is available [here](/packages/mistralai_gcp/RE
 * [retrieve](docs/sdks/files/README.md#retrieve) - Retrieve File
 * [delete](docs/sdks/files/README.md#delete) - Delete File
 
-### [fine_tuning](docs/sdks/finetuning/README.md)
 
-* [list_jobs](docs/sdks/finetuning/README.md#list_jobs) - Get Fine Tuning Jobs
-* [create_job](docs/sdks/finetuning/README.md#create_job) - Create Fine Tuning Job
-* [get_job](docs/sdks/finetuning/README.md#get_job) - Get Fine Tuning Job
-* [cancel_job](docs/sdks/finetuning/README.md#cancel_job) - Cancel Fine Tuning Job
-* [start_job](docs/sdks/finetuning/README.md#start_job) - Start Fine Tuning Job
+### [fine_tuning.jobs](docs/sdks/jobs/README.md)
+
+* [list](docs/sdks/jobs/README.md#list) - Get Fine Tuning Jobs
+* [create](docs/sdks/jobs/README.md#create) - Create Fine Tuning Job
+* [get](docs/sdks/jobs/README.md#get) - Get Fine Tuning Job
+* [cancel](docs/sdks/jobs/README.md#cancel) - Cancel Fine Tuning Job
+* [start](docs/sdks/jobs/README.md#start) - Start Fine Tuning Job
 
 ### [chat](docs/sdks/chat/README.md)
 
-* [create](docs/sdks/chat/README.md#create) - Chat Completion
+* [complete](docs/sdks/chat/README.md#complete) - Chat Completion
 * [stream](docs/sdks/chat/README.md#stream) - Stream chat completion
 
 ### [fim](docs/sdks/fim/README.md)
 
-* [create](docs/sdks/fim/README.md#create) - Fim Completion
+* [complete](docs/sdks/fim/README.md#complete) - Fim Completion
 * [stream](docs/sdks/fim/README.md#stream) - Stream fim completion
 
+### [agents](docs/sdks/agents/README.md)
+
+* [complete](docs/sdks/agents/README.md#complete) - Chat Completion
+* [stream](docs/sdks/agents/README.md#stream) - Stream Agents completion
+
 ### [embeddings](docs/sdks/embeddings/README.md)
 
 * [create](docs/sdks/embeddings/README.md#create) - Embeddings
@@ -297,12 +355,12 @@ s = Mistral(
 )
 
 
-res = s.chat.stream(messages=[
+res = s.chat.stream(model="mistral-small-latest", messages=[
     {
         "content": "Who is the best French painter? Answer in one short sentence.",
         "role": "user",
     },
-], model="mistral-small-latest")
+])
 
 if res is not None:
     for event in res:
@@ -397,10 +455,10 @@ if res is not None:
 
 Handling errors in this SDK should largely match your expectations.  All operations return a response object or raise an error.  If Error objects are specified in your OpenAPI Spec, the SDK will raise the appropriate Error type.
 
-| Error Object               | Status Code | Content Type     |
-| -------------------------- | ----------- | ---------------- |
-| models.HTTPValidationError | 422         | application/json |
-| models.SDKError            | 4xx-5xx     | */*              |
+| Error Object               | Status Code                | Content Type               |
+| -------------------------- | -------------------------- | -------------------------- |
+| models.HTTPValidationError | 422                        | application/json           |
+| models.SDKError            | 4xx-5xx                    | */*                        |
 
 ### Example
 
@@ -437,9 +495,9 @@ if res is not None:
 
 You can override the default server globally by passing a server name to the `server: str` optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the names associated with the available servers:
 
-| Name   | Server                   | Variables |
-| ------ | ------------------------ | --------- |
-| `prod` | `https://api.mistral.ai` | None      |
+| Name | Server | Variables |
+| ----- | ------ | --------- |
+| `prod` | `https://api.mistral.ai` | None |
 
 #### Example
 
@@ -572,11 +630,11 @@ s = Mistral(async_client=CustomClient(httpx.AsyncClient()))
 
 This SDK supports the following security scheme globally:
 
-| Name      | Type | Scheme      |
-| --------- | ---- | ----------- |
-| `api_key` | http | HTTP Bearer |
+| Name                 | Type                 | Scheme               | Environment Variable |
+| -------------------- | -------------------- | -------------------- | -------------------- |
+| `api_key`            | http                 | HTTP Bearer          | `MISTRAL_API_KEY`    |
 
-To authenticate with the API the `api_key` parameter must be set when initializing the SDK client instance. For example:
+To authenticate with the API the `null` parameter must be set when initializing the SDK client instance. For example:
 ```python
 from mistralai import Mistral
 import os
@@ -594,13 +652,20 @@ if res is not None:
 
 ```
 <!-- End Authentication [security] -->
-## Providers Support
 
-We also provide provider specific SDK for:
+<!-- Start Debugging [debug] -->
+## Debugging
 
-- [GCP](packages/mistralai_gcp/README.md)
-- [Azure](packages/mistralai_azure/README.md)
+To emit debug logs for SDK requests and responses you can pass a logger object directly into your SDK object.
 
+```python
+from mistralai import Mistral
+import logging
+
+logging.basicConfig(level=logging.DEBUG)
+s = Mistral(debug_logger=logging.getLogger("mistralai"))
+```
+<!-- End Debugging [debug] -->
 
 <!-- Placeholder for Future Speakeasy SDK Sections -->