> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentops.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Mistral
> AgentOps provides first class support for Mistral AI's models
[Mistral](https://mistral.ai) publishes open-weight AI models that can be used for a variety of tasks. To develop with Mistral, visit their developer docs [here](https://docs.mistral.ai).
## Steps to Integrate Mistral with AgentOps
```bash pip theme={null}
pip install agentops
```
```bash poetry theme={null}
poetry add agentops
```
```bash pip theme={null}
pip install mistralai
```
```bash poetry theme={null}
poetry add mistralai
```
Make sure to call `agentops.init` before calling any `openai`, `cohere`, `crew`, etc models.
```python python theme={null}
from mistralai import Mistral
import agentops
agentops.init()
client = Mistral(api_key="your_api_key")
# Your code here...
agentops.end_session('Success')
```
Set your API key as an `.env` variable for easy access.
```python .env theme={null}
AGENTOPS_API_KEY=
MISTRAL_API_KEY=
```
Execute your program and visit [app.agentops.ai/drilldown](https://app.agentops.ai/drilldown) to observe your Agent! 🕵️
After your run, AgentOps prints a clickable url to console linking directly to your session in the Dashboard
## Full Examples
A notebook demonstrating how to use AgentOps with Mistral can be found [here](https://github.com/AgentOps-AI/agentops/blob/main/examples/mistral_examples/mistral_example.ipynb).
```python sync theme={null}
from mistralai import Mistral
import agentops
agentops.init()
client = Mistral(api_key="your_api_key")
response = client.chat.complete(
model="mistral-small-latest",
messages=[
{
"role": "user",
"content": "Explain the history of the French Revolution."
}
],
)
print(response.choices[0].message.content)
agentops.end_session('Success')
```
```python async theme={null}
import asyncio
from mistralai import Mistral
import agentops
async def main():
agentops.init()
client = Mistral(api_key="your_api_key")
response = await client.chat.complete_async(
model="mistral-small-latest",
messages=[
{
"role": "user",
"content": "Write a short summary about the poem La Belle Dame sans Merci.",
},
],
)
print(response.choices[0].message.content)
agentops.end_session('Success')
asyncio.run(main())
```
### Streaming Examples
```python sync theme={null}
from mistralai import Mistral
import agentops
agentops.init()
client = Mistral(api_key="your_api_key")
complete_response = ""
response = client.chat.stream(
model="mistral-small-latest",
messages=[
{
"role": "user",
"content": "Who was Joan of Arc?"
}
],
)
for chunk in response:
if chunk.data.choices[0].finish_reason == "stop":
print(complete_response)
else:
complete_response += chunk.data.choices[0].delta.content
agentops.end_session('Success')
```
```python async theme={null}
import asyncio
from mistralai import Mistral
import agentops
async def main():
agentops.init()
client = Mistral(api_key="your_api_key")
complete_response = ""
response = await client.chat.stream_async(
model="mistral-small-latest",
messages=[
{
"role": "user",
"content": "Write a short summary about the poem La Belle Dame sans Merci.",
},
],
)
async for chunk in response:
if chunk.data.choices[0].finish_reason == "stop":
print(complete_response)
else:
complete_response += chunk.data.choices[0].delta.content
agentops.end_session('Success')
asyncio.run(main())
```