llamaIndex - ✅(Solved) Fix [Feature Request]: Mistral Azure SDK [1 pull requests, 1 participants]

llamaIndex2026-02-10 11:09:48

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

run-llama/llama_index#20667•Fetched 2026-04-08 00:31:37

View on GitHub

Comments

Participants

Timeline

Reactions

Author

RiccardoRubini

Participants

RiccardoRubini

Timeline (top)

labeled ×2closed ×1cross-referenced ×1

Error Message

content += content_delta │ └ [{'reference_ids': [1], 'type': 'reference'}] └ "Papa Waigo N'Diaye è un ex calciatore senegalese..."

TypeError: can only concatenate str (not "list") to str

Root Cause

Why? This because Mistral models frequently return ReferenceChunk objects during streaming (refer to Mistral Citations). The OpenAILike class assumes all delta content is a string, leading to a TypeError during stream concatenation

Code Example

content += content_delta
    │          └ [{'reference_ids': [1], 'type': 'reference'}]
    └ "Papa Waigo N'Diaye è un ex calciatore senegalese..."

TypeError: can only concatenate str (not "list") to str

RAW_BUFFERClick to expand / collapse

Feature Description

Currently, the only way to use Mistral models deployed via Azure AI Foundry within LlamaIndex is through the OpenAILike class. However, this approach is insufficient when dealing with specific Mistral features such as Citations.

content += content_delta
    │          └ [{'reference_ids': [1], 'type': 'reference'}]
    └ "Papa Waigo N'Diaye è un ex calciatore senegalese..."

TypeError: can only concatenate str (not "list") to str

Add native support for the Mistral Azure SDK within LlamaIndex. This new provider should:

Support Azure AI Foundry authentication and endpoint structures.
Implement the same streaming logic used in the base MistralAI class to correctly handle or filter ReferenceChunks.

Reason

No response

Value of Feature

No response

extent analysis

Fix Plan

To add native support for the Mistral Azure SDK within LlamaIndex, we will create a new provider class that handles Azure AI Foundry authentication and endpoint structures, as well as implements the correct streaming logic for ReferenceChunks.

Step-by-Step Solution

Create a new class MistralAzureProvider that inherits from the base MistralAI class.
Implement the __init__ method to handle Azure AI Foundry authentication and endpoint structures.
Override the stream method to correctly handle ReferenceChunks.
Add error handling for cases where ReferenceChunks are not supported.

Example Code

import requests
from mistral.azure import MistralAzure

class MistralAzureProvider:
    def __init__(self, endpoint, api_key):
        self.endpoint = endpoint
        self.api_key = api_key
        self.mistral_azure = MistralAzure(endpoint, api_key)

    def stream(self, prompt, max_tokens):
        response = self.mistral_azure.stream(prompt, max_tokens)
        content = ""
        for delta in response:
            if isinstance(delta, str):
                content += delta
            elif isinstance(delta, dict) and delta.get("type") == "reference":
                # Handle ReferenceChunk
                reference_ids = delta.get("reference_ids")
                # Filter or process ReferenceChunk as needed
                content += f"Reference: {reference_ids}"
            else:
                raise ValueError("Unsupported delta type")
        return content

Verification

To verify that the fix worked, test the MistralAzureProvider class with a sample prompt and max tokens, and check that the response correctly handles ReferenceChunks.

Extra Tips

Make sure to handle errors and exceptions properly, especially when dealing with external APIs and authentication.
Consider adding logging and monitoring to track issues and improve the overall reliability of the system.
Refer to the Mistral Azure SDK documentation for more information on authentication and endpoint structures.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #ssr #installation #tensor shape #autograd error #GPU setup #container setup #orchestration issue #cache issue #memory leak

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

llamaIndex - ✅(Solved) Fix [Feature Request]: Mistral Azure SDK [1 pull requests, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fixed

PR fix notes

PR #20668: Rrubini/mistral azure sdk

Description (problem / solution / changelog)

Description

New Package?

Version Bump?

Type of Change

How Has This Been Tested?

Suggested Checklist:

Testing Note

Changed files