mirror of
https://github.com/deepset-ai/haystack.git
synced 2026-10-12 02:12:50 +00:00
docs: update Mistral model names in component pages (#13155)
This commit is contained in:
Bilge Yücel
@@ -36,7 +36,7 @@ The component returns one Haystack [`Document`](../../concepts/data-classes.mdx#
|
||||
|
||||
By default, the component uses the `MISTRAL_API_KEY` environment variable for authentication. You can also pass an `api_key` at initialization. Local files are automatically uploaded to Mistral's storage for processing and deleted afterward (configurable with `cleanup_uploaded_files`).
|
||||
|
||||
When you initialize the component, you can optionally specify which pages to process, set limits on image extraction, configure minimum image sizes, or include base64-encoded images in the response. The default model is `"mistral-ocr-4-1"`. See the [Mistral models documentation](https://docs.mistral.ai/getting-started/models/models_overview/) for available models.
|
||||
When you initialize the component, you can optionally specify which pages to process, set limits on image extraction, configure minimum image sizes, or include base64-encoded images in the response. The default model is `"mistral-ocr-4-1"`. You can also use `"mistral-ocr-latest"` or the earlier `"mistral-ocr-3-0"`. See the [Mistral models documentation](https://docs.mistral.ai/models) for available models.
|
||||
|
||||
### Structured Annotations
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ This component should be used to embed a list of Documents. To embed a string, u
|
||||
|
||||
`MistralDocumentEmbedder` computes the embeddings of a list of documents and stores the obtained vectors in the embedding field of each document. It uses the Mistral API and its embedding models.
|
||||
|
||||
The component currently supports the `mistral-embed` embedding model. The list of all supported models can be found in Mistral’s [embedding models documentation](https://docs.mistral.ai/platform/endpoints/#embedding-models).
|
||||
The component supports the `mistral-embed` (default) and `codestral-embed` embedding models. The list of all supported models can be found in Mistral’s [models documentation](https://docs.mistral.ai/models).
|
||||
|
||||
To start using this integration with Haystack, install it with:
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ Use `MistralTextEmbedder` to embed a simple string (such as a query) into a vect
|
||||
|
||||
`MistralTextEmbedder` transforms a string into a vector that captures its semantics using a Mistral embedding model.
|
||||
|
||||
The component currently supports the `mistral-embed` embedding model. The list of all supported models can be found in Mistral’s [embedding models documentation](https://docs.mistral.ai/platform/endpoints/#embedding-models).
|
||||
The component supports the `mistral-embed` (default) and `codestral-embed` embedding models. The list of all supported models can be found in Mistral’s [models documentation](https://docs.mistral.ai/models).
|
||||
|
||||
To start using this integration with Haystack, install it with:
|
||||
|
||||
|
||||
@@ -26,20 +26,24 @@ This component enables chat completion using Mistral’s text generation models.
|
||||
|
||||
## Overview
|
||||
|
||||
This integration supports Mistral’s models provided through the generative endpoint. For a full list of available models, check out the [Mistral documentation](https://docs.mistral.ai/platform/endpoints/#generative-endpoints).
|
||||
This integration supports Mistral’s models provided through the generative endpoint. For a full list of available models, check out the [Mistral documentation](https://docs.mistral.ai/models).
|
||||
|
||||
`MistralChatGenerator` needs a Mistral API key to work. You can write this key in:
|
||||
|
||||
- The `api_key` init parameter using [Secret API](../../concepts/secret-management.mdx)
|
||||
- The `MISTRAL_API_KEY` environment variable (recommended)
|
||||
|
||||
Currently, available models are:
|
||||
Some of the available models are:
|
||||
|
||||
- `mistral-small-latest` (default)
|
||||
- `mistral-medium-latest`
|
||||
- `mistral-large-latest`
|
||||
- `mistral-large-4`
|
||||
- `ministral-14b-latest`
|
||||
- `codestral-latest`
|
||||
|
||||
The `MistralChatGenerator.SUPPORTED_MODELS` attribute holds the complete list of chat models.
|
||||
|
||||
This component needs a list of [`ChatMessage`](../../concepts/data-classes/chatmessage.mdx) objects to operate. `ChatMessage` is a data class that contains a message, a role (who generated the message, such as `user`, `assistant`, `system`, `tool`), and optional metadata.
|
||||
|
||||
Refer to the [Mistral API documentation](https://docs.mistral.ai/api/#operation/createChatCompletion) for more details on the parameters supported by the Mistral API, which you can provide with `generation_kwargs` when running the component.
|
||||
@@ -111,7 +115,7 @@ With multimodal inputs:
|
||||
from haystack.dataclasses import ChatMessage, ImageContent
|
||||
from haystack_integrations.components.generators.mistral import MistralChatGenerator
|
||||
|
||||
llm = MistralChatGenerator(model="pixtral-12b-2409")
|
||||
llm = MistralChatGenerator(model="mistral-large-4")
|
||||
|
||||
image = ImageContent.from_file_path("apple.jpg")
|
||||
user_message = ChatMessage.from_user(
|
||||
@@ -144,7 +148,7 @@ converter = HTMLToDocument()
|
||||
prompt_builder = ChatPromptBuilder(variables=["documents"])
|
||||
llm = MistralChatGenerator(
|
||||
streaming_callback=print_streaming_chunk,
|
||||
model="mistral-small",
|
||||
model="mistral-large-4",
|
||||
)
|
||||
|
||||
message_template = """Answer the following question based on the contents of the article: {{query}}\n
|
||||
|
||||
+1
-1
@@ -36,7 +36,7 @@ The component returns one Haystack [`Document`](../../concepts/data-classes.mdx#
|
||||
|
||||
By default, the component uses the `MISTRAL_API_KEY` environment variable for authentication. You can also pass an `api_key` at initialization. Local files are automatically uploaded to Mistral's storage for processing and deleted afterward (configurable with `cleanup_uploaded_files`).
|
||||
|
||||
When you initialize the component, you can optionally specify which pages to process, set limits on image extraction, configure minimum image sizes, or include base64-encoded images in the response. The default model is `"mistral-ocr-4-1"`. See the [Mistral models documentation](https://docs.mistral.ai/getting-started/models/models_overview/) for available models.
|
||||
When you initialize the component, you can optionally specify which pages to process, set limits on image extraction, configure minimum image sizes, or include base64-encoded images in the response. The default model is `"mistral-ocr-4-1"`. You can also use `"mistral-ocr-latest"` or the earlier `"mistral-ocr-3-0"`. See the [Mistral models documentation](https://docs.mistral.ai/models) for available models.
|
||||
|
||||
### Structured Annotations
|
||||
|
||||
|
||||
+1
-1
@@ -30,7 +30,7 @@ This component should be used to embed a list of Documents. To embed a string, u
|
||||
|
||||
`MistralDocumentEmbedder` computes the embeddings of a list of documents and stores the obtained vectors in the embedding field of each document. It uses the Mistral API and its embedding models.
|
||||
|
||||
The component currently supports the `mistral-embed` embedding model. The list of all supported models can be found in Mistral’s [embedding models documentation](https://docs.mistral.ai/platform/endpoints/#embedding-models).
|
||||
The component supports the `mistral-embed` (default) and `codestral-embed` embedding models. The list of all supported models can be found in Mistral’s [models documentation](https://docs.mistral.ai/models).
|
||||
|
||||
To start using this integration with Haystack, install it with:
|
||||
|
||||
|
||||
+1
-1
@@ -30,7 +30,7 @@ Use `MistralTextEmbedder` to embed a simple string (such as a query) into a vect
|
||||
|
||||
`MistralTextEmbedder` transforms a string into a vector that captures its semantics using a Mistral embedding model.
|
||||
|
||||
The component currently supports the `mistral-embed` embedding model. The list of all supported models can be found in Mistral’s [embedding models documentation](https://docs.mistral.ai/platform/endpoints/#embedding-models).
|
||||
The component supports the `mistral-embed` (default) and `codestral-embed` embedding models. The list of all supported models can be found in Mistral’s [models documentation](https://docs.mistral.ai/models).
|
||||
|
||||
To start using this integration with Haystack, install it with:
|
||||
|
||||
|
||||
+8
-4
@@ -26,20 +26,24 @@ This component enables chat completion using Mistral’s text generation models.
|
||||
|
||||
## Overview
|
||||
|
||||
This integration supports Mistral’s models provided through the generative endpoint. For a full list of available models, check out the [Mistral documentation](https://docs.mistral.ai/platform/endpoints/#generative-endpoints).
|
||||
This integration supports Mistral’s models provided through the generative endpoint. For a full list of available models, check out the [Mistral documentation](https://docs.mistral.ai/models).
|
||||
|
||||
`MistralChatGenerator` needs a Mistral API key to work. You can write this key in:
|
||||
|
||||
- The `api_key` init parameter using [Secret API](../../concepts/secret-management.mdx)
|
||||
- The `MISTRAL_API_KEY` environment variable (recommended)
|
||||
|
||||
Currently, available models are:
|
||||
Some of the available models are:
|
||||
|
||||
- `mistral-small-latest` (default)
|
||||
- `mistral-medium-latest`
|
||||
- `mistral-large-latest`
|
||||
- `mistral-large-4`
|
||||
- `ministral-14b-latest`
|
||||
- `codestral-latest`
|
||||
|
||||
The `MistralChatGenerator.SUPPORTED_MODELS` attribute holds the complete list of chat models.
|
||||
|
||||
This component needs a list of [`ChatMessage`](../../concepts/data-classes/chatmessage.mdx) objects to operate. `ChatMessage` is a data class that contains a message, a role (who generated the message, such as `user`, `assistant`, `system`, `tool`), and optional metadata.
|
||||
|
||||
Refer to the [Mistral API documentation](https://docs.mistral.ai/api/#operation/createChatCompletion) for more details on the parameters supported by the Mistral API, which you can provide with `generation_kwargs` when running the component.
|
||||
@@ -111,7 +115,7 @@ With multimodal inputs:
|
||||
from haystack.dataclasses import ChatMessage, ImageContent
|
||||
from haystack_integrations.components.generators.mistral import MistralChatGenerator
|
||||
|
||||
llm = MistralChatGenerator(model="pixtral-12b-2409")
|
||||
llm = MistralChatGenerator(model="mistral-large-4")
|
||||
|
||||
image = ImageContent.from_file_path("apple.jpg")
|
||||
user_message = ChatMessage.from_user(
|
||||
@@ -144,7 +148,7 @@ converter = HTMLToDocument()
|
||||
prompt_builder = ChatPromptBuilder(variables=["documents"])
|
||||
llm = MistralChatGenerator(
|
||||
streaming_callback=print_streaming_chunk,
|
||||
model="mistral-small",
|
||||
model="mistral-large-4",
|
||||
)
|
||||
|
||||
message_template = """Answer the following question based on the contents of the article: {{query}}\n
|
||||
|
||||
Reference in New Issue
Block a user