mistralai 0.5.5a50__tar.gz → 1.0.0rc2__tar.gz

{mistralai-0.5.5a50 → mistralai-1.0.0rc2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mistralai
-Version: 0.5.5a50
+Version: 1.0.0rc2
 Summary: Python Client SDK for the Mistral AI API.
 Author: Mistral
 Requires-Python: >=3.8,<4.0
@@ -28,7 +28,6 @@ Description-Content-Type: text/markdown
 
 ## Migration warning
  
-TODO: provide more details
 This documentation is for Mistralai SDK v1. You can find more details on how to migrate from v0 to v1 [here](MIGRATION.md)
 
 <!-- Start SDK Installation [installation] -->
@@ -62,12 +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
@@ -87,12 +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
@@ -145,19 +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] -->
 
-### Azure AI
+## Providers' SDKs Example Usage
 
-TODO ADJUST LINKS
+### 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.py).
+Here's a basic example to get you started. You can also run [the example in the `examples` directory](/examples/azure).
 
 ```python
 import asyncio
@@ -167,35 +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 [GCP](packages/mistralai-azure/README.md).
+The documentation for the Azure SDK is available [here](packages/mistralai_azure/README.md).
 
 ### Google Cloud
 
-TODO ADJUST LINKS
 
 **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
 
@@ -223,23 +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 [GCP](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] -->
@@ -261,24 +308,30 @@ The documentation for the GCP SDK is available [GCP](packages/mistralai_gcp/READ
 * [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
@@ -302,12 +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:
@@ -577,11 +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
@@ -599,13 +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 -->
 

{mistralai-0.5.5a50 → mistralai-1.0.0rc2}/README.md

@@ -6,7 +6,6 @@
 
 ## Migration warning
  
-TODO: provide more details
 This documentation is for Mistralai SDK v1. You can find more details on how to migrate from v0 to v1 [here](MIGRATION.md)
 
 <!-- Start SDK Installation [installation] -->
@@ -40,12 +39,12 @@ 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
@@ -65,12 +64,12 @@ 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
@@ -123,19 +122,72 @@ 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] -->
 
-### Azure AI
+## Providers' SDKs Example Usage
 
-TODO ADJUST LINKS
+### 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.py).
+Here's a basic example to get you started. You can also run [the example in the `examples` directory](/examples/azure).
 
 ```python
 import asyncio
@@ -145,35 +197,32 @@ 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 [GCP](packages/mistralai-azure/README.md).
+The documentation for the Azure SDK is available [here](packages/mistralai_azure/README.md).
 
 ### Google Cloud
 
-TODO ADJUST LINKS
 
 **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
 
@@ -201,23 +250,21 @@ 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 [GCP](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] -->
@@ -239,24 +286,30 @@ The documentation for the GCP SDK is available [GCP](packages/mistralai_gcp/READ
 * [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
@@ -280,12 +333,12 @@ 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:
@@ -555,11 +608,11 @@ 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
@@ -577,13 +630,20 @@ 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 -->