feat: Adding MistralAI mode (#2065)

* Adding MistralAI mode

* Update embedding_component.py

* Update ui.py

* Update settings.py

* Update embedding_component.py

* Update settings.py

* Update settings.py

* Update settings-mistral.yaml

* Update llm_component.py

* Update settings-mistral.yaml

* Update settings.py

* Update settings.py

* Update ui.py

* Update embedding_component.py

* Delete settings-mistral.yaml

---------

Co-authored-by: SkiingIsFun123 <101684827+SkiingIsFun123@users.noreply.github.com>
Co-authored-by: Javier Martinez <javiermartinezalvarez98@gmail.com>

poetry.lock

@@ -2238,6 +2238,17 @@ files = [
     {file = "joblib-1.4.2.tar.gz", hash = "sha256:2382c5816b2636fbd20a09e0f4e9dad4736765fdfb7dca582943b9c1366b3f0e"},
 ]
 
+[[package]]
+name = "jsonpath-python"
+version = "1.0.6"
+description = "A more powerful JSONPath implementation in modern python"
+optional = true
+python-versions = ">=3.6"
+files = [
+    {file = "jsonpath-python-1.0.6.tar.gz", hash = "sha256:dd5be4a72d8a2995c3f583cf82bf3cd1a9544cfdabf2d22595b67aff07349666"},
+    {file = "jsonpath_python-1.0.6-py3-none-any.whl", hash = "sha256:1e3b78df579f5efc23565293612decee04214609208a2335884b3ee3f786b575"},
+]
+
 [[package]]
 name = "kiwisolver"
 version = "1.4.5"
@@ -2481,6 +2492,21 @@ huggingface-hub = {version = ">=0.19.0", extras = ["inference"]}
 llama-index-core = ">=0.10.1,<0.11.0"
 sentence-transformers = ">=2.6.1"
 
+[[package]]
+name = "llama-index-embeddings-mistralai"
+version = "0.1.6"
+description = "llama-index embeddings mistralai integration"
+optional = true
+python-versions = "<4.0,>=3.9"
+files = [
+    {file = "llama_index_embeddings_mistralai-0.1.6-py3-none-any.whl", hash = "sha256:d69d6fc0be8a1772aaf890bc036f2d575af46070b375a2649803c0eb9736ea1b"},
+    {file = "llama_index_embeddings_mistralai-0.1.6.tar.gz", hash = "sha256:7c9cbf974b1e7d14ded34d3eb749a0d1a379fb151ab75115cc1ffdd08a96a045"},
+]
+
+[package.dependencies]
+llama-index-core = ">=0.10.1,<0.11.0"
+mistralai = ">=1.0.0"
+
 [[package]]
 name = "llama-index-embeddings-ollama"
 version = "0.1.2"
@@ -3002,6 +3028,27 @@ files = [
     {file = "minijinja-2.0.1.tar.gz", hash = "sha256:e774beffebfb8a1ad17e638ef70917cf5e94593f79acb8a8fff7d983169f3a4e"},
 ]
 
+[[package]]
+name = "mistralai"
+version = "1.0.3"
+description = "Python Client SDK for the Mistral AI API."
+optional = true
+python-versions = "<4.0,>=3.8"
+files = [
+    {file = "mistralai-1.0.3-py3-none-any.whl", hash = "sha256:64af7c9192e64dc66b2da6d1c4d54a1324a881c21665a2f93d6b35d9de9f87c8"},
+    {file = "mistralai-1.0.3.tar.gz", hash = "sha256:84f1a217666c76fec9d477ae266399b813c3ac32a4a348d2ecd5fe1c039b0667"},
+]
+
+[package.dependencies]
+httpx = ">=0.27.0,<0.28.0"
+jsonpath-python = ">=1.0.6,<2.0.0"
+pydantic = ">=2.8.2,<2.9.0"
+python-dateutil = ">=2.9.0.post0,<3.0.0"
+typing-inspect = ">=0.9.0,<0.10.0"
+
+[package.extras]
+gcp = ["google-auth (==2.27.0)", "requests (>=2.32.3,<3.0.0)"]
+
 [[package]]
 name = "mmh3"
 version = "4.1.0"
@@ -6692,6 +6739,7 @@ cffi = ["cffi (>=1.11)"]
 embeddings-azopenai = ["llama-index-embeddings-azure-openai"]
 embeddings-gemini = ["llama-index-embeddings-gemini"]
 embeddings-huggingface = ["einops", "llama-index-embeddings-huggingface"]
+embeddings-mistral = ["llama-index-embeddings-mistralai"]
 embeddings-ollama = ["llama-index-embeddings-ollama", "ollama"]
 embeddings-openai = ["llama-index-embeddings-openai"]
 embeddings-sagemaker = ["boto3"]
@@ -6714,4 +6762,4 @@ vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.11,<3.12"
-content-hash = "45264d80672084e35ca0ea11b368a29001a3b9003822bddc67fb18489a8fe519"
+content-hash = "3fa6ef447847895b1a16b8b0422dd9e4fda1aaaadef3af71971eb412da89bf67"

private_gpt/components/embedding/embedding_component.py

@@ -144,6 +144,23 @@ class EmbeddingComponent:
                     api_key=settings.gemini.api_key,
                     model_name=settings.gemini.embedding_model,
                 )
+            case "mistralai":
+                try:
+                    from llama_index.embeddings.mistralai import (  # type: ignore
+                        MistralAIEmbedding,
+                    )
+                except ImportError as e:
+                    raise ImportError(
+                        "Mistral dependencies not found, install with `poetry install --extras embeddings-mistral`"
+                    ) from e
+
+                api_key = settings.openai.api_key
+                model = settings.openai.embedding_model
+
+                self.embedding_model = MistralAIEmbedding(
+                    api_key=api_key,
+                    model=model,
+                )
             case "mock":
                 # Not a random number, is the dimensionality used by
                 # the default embedding model

private_gpt/settings/settings.py

@@ -197,7 +197,14 @@ class HuggingFaceSettings(BaseModel):
 
 class EmbeddingSettings(BaseModel):
     mode: Literal[
-        "huggingface", "openai", "azopenai", "sagemaker", "ollama", "mock", "gemini"
+        "huggingface",
+        "openai",
+        "azopenai",
+        "sagemaker",
+        "ollama",
+        "mock",
+        "gemini",
+        "mistralai",
     ]
     ingest_mode: Literal["simple", "batch", "parallel", "pipeline"] = Field(
         "simple",

pyproject.toml

@@ -30,6 +30,7 @@ llama-index-embeddings-huggingface = {version ="^0.2.2", optional = true}
 llama-index-embeddings-openai = {version ="^0.1.10", optional = true}
 llama-index-embeddings-azure-openai = {version ="^0.1.10", optional = true}
 llama-index-embeddings-gemini = {version ="^0.1.8", optional = true}
+llama-index-embeddings-mistralai = {version ="^0.1.6", optional = true}
 llama-index-vector-stores-qdrant = {version ="^0.2.10", optional = true}
 llama-index-vector-stores-milvus = {version ="^0.1.20", optional = true}
 llama-index-vector-stores-chroma = {version ="^0.1.10", optional = true}
@@ -83,6 +84,7 @@ embeddings-openai = ["llama-index-embeddings-openai"]
 embeddings-sagemaker = ["boto3"]
 embeddings-azopenai = ["llama-index-embeddings-azure-openai"]
 embeddings-gemini = ["llama-index-embeddings-gemini"]
+embeddings-mistral = ["llama-index-embeddings-mistralai"]
 vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
 vector-stores-clickhouse = ["llama-index-vector-stores-clickhouse", "clickhouse_connect"]
 vector-stores-chroma = ["llama-index-vector-stores-chroma"]