Clarifai : Added Clarifai as LLM and embedding model provider. (#1311)

Co-authored-by: Deshraj Yadav <deshraj@gatech.edu>

configs/clarifai.yaml

@@ -0,0 +1,12 @@
+llm:
+  provider: clarifai
+  config: 
+    model: "https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct"
+    model_kwargs: 
+      temperature: 0.5
+      max_tokens: 1000
+
+embedder:
+  provider: clarifai
+  config: 
+    model: "https://clarifai.com/clarifai/main/models/BAAI-bge-base-en-v15"

docs/components/embedding-models.mdx

@@ -16,6 +16,7 @@ Embedchain supports several embedding models from the following providers:
   <Card title="NVIDIA AI" href="#nvidia-ai"></Card>
   <Card title="Cohere" href="#cohere"></Card>
   <Card title="Ollama" href="#ollama"></Card>
+  <Card title="Clarifai" href="#clarifai"></Card>
 </CardGroup>
 
 ## OpenAI
@@ -385,4 +386,51 @@ embedder:
     model: 'all-minilm:latest'
 ```
 
+</CodeGroup>
+
+## Clarifai
+
+Install related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[clarifai]'
+```
+
+set the `CLARIFAI_PAT` as environment variable which you can find in the [security page](https://clarifai.com/settings/security). Optionally you can also pass the PAT key as parameters in LLM/Embedder class.
+
+Now you are all set with exploring Embedchain.
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["CLARIFAI_PAT"] = "XXX"
+
+# load llm and embedder configuration from config.yaml file
+app = App.from_config(config_path="config.yaml")
+
+#Now let's add some data.
+app.add("https://www.forbes.com/profile/elon-musk")
+
+#Query the app
+response = app.query("what college degrees does elon musk have?")
+```
+Head to [Clarifai Platform](https://clarifai.com/explore/models?page=1&perPage=24&filterData=%5B%7B%22field%22%3A%22output_fields%22%2C%22value%22%3A%5B%22embeddings%22%5D%7D%5D) to explore all the State of the Art embedding models available to use.
+For passing LLM model inference parameters use `model_kwargs` argument in the config file. Also you can use `api_key` argument to pass `CLARIFAI_PAT` in the config.
+
+```yaml config.yaml
+llm:
+ provider: clarifai
+ config:
+   model: "https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct"
+   model_kwargs:
+     temperature: 0.5
+     max_tokens: 1000  
+embedder:
+ provider: clarifai
+ config:
+   model: "https://clarifai.com/clarifai/main/models/BAAI-bge-base-en-v15"
+```
 </CodeGroup>

docs/components/llms.mdx

@@ -15,6 +15,7 @@ Embedchain comes with built-in support for various popular large language models
   <Card title="Together" href="#together"></Card>
   <Card title="Ollama" href="#ollama"></Card>
   <Card title="vLLM" href="#vllm"></Card>
+  <Card title="Clarifai" href="#clarifai"></Card>
   <Card title="GPT4All" href="#gpt4all"></Card>
   <Card title="JinaChat" href="#jinachat"></Card>
   <Card title="Hugging Face" href="#hugging-face"></Card>
@@ -385,6 +386,54 @@ llm:
 
 </CodeGroup>
 
+## Clarifai
+
+Install related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[clarifai]'
+```
+
+set the `CLARIFAI_PAT` as environment variable which you can find in the [security page](https://clarifai.com/settings/security). Optionally you can also pass the PAT key as parameters in LLM/Embedder class.
+
+Now you are all set with exploring Embedchain.
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["CLARIFAI_PAT"] = "XXX"
+
+# load llm configuration from config.yaml file
+app = App.from_config(config_path="config.yaml")
+
+#Now let's add some data.
+app.add("https://www.forbes.com/profile/elon-musk")
+
+#Query the app
+response = app.query("what college degrees does elon musk have?")
+```
+Head to [Clarifai Platform](https://clarifai.com/explore/models?page=1&perPage=24&filterData=%5B%7B%22field%22%3A%22use_cases%22%2C%22value%22%3A%5B%22llm%22%5D%7D%5D) to browse various State-of-the-Art LLM models for your use case.
+For passing model inference parameters use `model_kwargs` argument in the config file. Also you can use `api_key` argument to pass `CLARIFAI_PAT` in the config.
+
+```yaml config.yaml
+llm:
+ provider: clarifai
+ config:
+   model: "https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct"
+   model_kwargs:
+     temperature: 0.5
+     max_tokens: 1000  
+embedder:
+ provider: clarifai
+ config:
+   model: "https://clarifai.com/clarifai/main/models/BAAI-bge-base-en-v15"
+```
+</CodeGroup>
+
+
 ## GPT4ALL
 
 Install related dependencies using the following command:

embedchain/embedder/clarifai.py

@@ -0,0 +1,52 @@
+import os
+from typing import Optional, Union
+
+from embedchain.config import BaseEmbedderConfig
+from embedchain.embedder.base import BaseEmbedder
+
+from chromadb import EmbeddingFunction, Embeddings
+
+
+class ClarifaiEmbeddingFunction(EmbeddingFunction):
+    def __init__(self, config: BaseEmbedderConfig) -> None:
+        super().__init__()
+        try:
+            from clarifai.client.model import Model
+            from clarifai.client.input import Inputs
+        except ModuleNotFoundError:
+            raise ModuleNotFoundError(
+                "The required dependencies for ClarifaiEmbeddingFunction are not installed."
+                'Please install with `pip install --upgrade "embedchain[clarifai]"`'
+            ) from None
+        self.config = config
+        self.api_key = config.api_key or os.getenv("CLARIFAI_PAT")
+        self.model = config.model
+        self.model_obj = Model(url=self.model, pat=self.api_key)
+        self.input_obj = Inputs(pat=self.api_key)
+
+    def __call__(self, input: Union[str, list[str]]) -> Embeddings:
+        if isinstance(input, str):
+            input = [input]
+
+        batch_size = 32
+        embeddings = []
+        try:
+            for i in range(0, len(input), batch_size):
+                batch = input[i : i + batch_size]
+                input_batch = [
+                    self.input_obj.get_text_input(input_id=str(id), raw_text=inp) for id, inp in enumerate(batch)
+                ]
+                response = self.model_obj.predict(input_batch)
+                embeddings.extend([list(output.data.embeddings[0].vector) for output in response.outputs])
+        except Exception as e:
+            print(f"Predict failed, exception: {e}")
+
+        return embeddings
+
+
+class ClarifaiEmbedder(BaseEmbedder):
+    def __init__(self, config: Optional[BaseEmbedderConfig] = None):
+        super().__init__(config)
+
+        embedding_func = ClarifaiEmbeddingFunction(config=self.config)
+        self.set_embedding_fn(embedding_fn=embedding_func)

embedchain/factory.py

@@ -23,6 +23,7 @@ class LlmFactory:
         "google": "embedchain.llm.google.GoogleLlm",
         "aws_bedrock": "embedchain.llm.aws_bedrock.AWSBedrockLlm",
         "mistralai": "embedchain.llm.mistralai.MistralAILlm",
+        "clarifai": "embedchain.llm.clarifai.ClarifaiLlm",
         "groq": "embedchain.llm.groq.GroqLlm",
         "nvidia": "embedchain.llm.nvidia.NvidiaLlm",
         "vllm": "embedchain.llm.vllm.VLLM",
@@ -56,6 +57,7 @@ class EmbedderFactory:
         "vertexai": "embedchain.embedder.vertexai.VertexAIEmbedder",
         "google": "embedchain.embedder.google.GoogleAIEmbedder",
         "mistralai": "embedchain.embedder.mistralai.MistralAIEmbedder",
+        "clarifai": "embedchain.embedder.clarifai.ClarifaiEmbedder",
         "nvidia": "embedchain.embedder.nvidia.NvidiaEmbedder",
         "cohere": "embedchain.embedder.cohere.CohereEmbedder",
         "ollama": "embedchain.embedder.ollama.OllamaEmbedder",
@@ -65,6 +67,7 @@ class EmbedderFactory:
         "google": "embedchain.config.embedder.google.GoogleAIEmbedderConfig",
         "gpt4all": "embedchain.config.embedder.base.BaseEmbedderConfig",
         "huggingface": "embedchain.config.embedder.base.BaseEmbedderConfig",
+        "clarifai": "embedchain.config.embedder.base.BaseEmbedderConfig",
         "openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
         "ollama": "embedchain.config.embedder.ollama.OllamaEmbedderConfig",
     }

embedchain/llm/clarifai.py

@@ -0,0 +1,47 @@
+import logging
+import os
+from typing import Optional
+
+from embedchain.config import BaseLlmConfig
+from embedchain.helpers.json_serializable import register_deserializable
+from embedchain.llm.base import BaseLlm
+
+
+@register_deserializable
+class ClarifaiLlm(BaseLlm):
+    def __init__(self, config: Optional[BaseLlmConfig] = None):
+        super().__init__(config=config)
+        if not self.config.api_key and "CLARIFAI_PAT" not in os.environ:
+            raise ValueError("Please set the CLARIFAI_PAT environment variable.")
+
+    def get_llm_model_answer(self, prompt):
+        return self._get_answer(prompt=prompt, config=self.config)
+
+    @staticmethod
+    def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
+        try:
+            from clarifai.client.model import Model
+        except ModuleNotFoundError:
+            raise ModuleNotFoundError(
+                "The required dependencies for Clarifai are not installed."
+                'Please install with `pip install --upgrade "embedchain[clarifai]"`'
+            ) from None
+
+        model_name = config.model
+        logging.info(f"Using clarifai LLM model: {model_name}")
+        api_key = config.api_key or os.getenv("CLARIFAI_PAT")
+        model = Model(url=model_name, pat=api_key)
+        params = config.model_kwargs
+
+        try:
+            (params := {}) if config.model_kwargs is None else config.model_kwargs
+            predict_response = model.predict_by_bytes(
+                bytes(prompt, "utf-8"),
+                input_type="text",
+                inference_params=params,
+            )
+            text = predict_response.outputs[0].data.text.raw
+            return text
+
+        except Exception as e:
+            logging.error(f"Predict failed, exception: {e}")

embedchain/utils/misc.py

@@ -414,6 +414,7 @@ def validate_config(config_data):
                     "google",
                     "aws_bedrock",
                     "mistralai",
+                    "clarifai",
                     "vllm",
                     "groq",
                     "nvidia",
@@ -458,6 +459,7 @@ def validate_config(config_data):
                     "azure_openai",
                     "google",
                     "mistralai",
+                    "clarifai",
                     "nvidia",
                     "ollama",
                     "cohere",
@@ -482,6 +484,7 @@ def validate_config(config_data):
                     "azure_openai",
                     "google",
                     "mistralai",
+                    "clarifai",
                     "nvidia",
                     "ollama",
                 ),

embedchain/vectordb/qdrant.py

@@ -251,4 +251,4 @@ class QdrantDB(BaseVectorDB):
 
     def delete(self, where: dict):
         db_filter = self._generate_query(where)
-        self.client.delete(collection_name=self.collection_name, points_selector=db_filter)
+        self.client.delete(collection_name=self.collection_name, points_selector=db_filter)

notebooks/clarifai.ipynb

@@ -0,0 +1,135 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Cookbook for using Clarifai LLM and Embedders with Embedchain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step-1: Install embedchain-clarifai package"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install embedchain[clarifai]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step-2: Set Clarifai PAT as env variable.\n",
+    "Sign-up to [Clarifai](https://clarifai.com/signup?utm_source=clarifai_home&utm_medium=direct&) platform and you can obtain `CLARIFAI_PAT` by following this [link](https://docs.clarifai.com/clarifai-basics/authentication/personal-access-tokens/).\n",
+    "\n",
+    "optionally you can also pass `api_key` in config of llm/embedder class."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from embedchain import App\n",
+    "\n",
+    "os.environ[\"CLARIFAI_PAT\"]=\"xxx\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step-3 Create embedchain app using clarifai LLM and embedder and define your config.\n",
+    "\n",
+    "Browse through Clarifai community page to get the URL of different [LLM](https://clarifai.com/explore/models?page=1&perPage=24&filterData=%5B%7B%22field%22%3A%22use_cases%22%2C%22value%22%3A%5B%22llm%22%5D%7D%5D) and [embedding](https://clarifai.com/explore/models?page=1&perPage=24&filterData=%5B%7B%22field%22%3A%22input_fields%22%2C%22value%22%3A%5B%22text%22%5D%7D%2C%7B%22field%22%3A%22output_fields%22%2C%22value%22%3A%5B%22embeddings%22%5D%7D%5D) models available."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Use model_kwargs to pass all model specific parameters for inference.\n",
+    "app = App.from_config(config={\n",
+    "    \"llm\": {\n",
+    "        \"provider\": \"clarifai\",\n",
+    "        \"config\": {\n",
+    "            \"model\": \"https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct\",\n",
+    "            \"model_kwargs\": {\n",
+    "            \"temperature\": 0.5,\n",
+    "            \"max_tokens\": 1000\n",
+    "            }\n",
+    "        }\n",
+    "    },\n",
+    "    \"embedder\": {\n",
+    "        \"provider\": \"clarifai\",\n",
+    "        \"config\": {\n",
+    "            \"model\": \"https://clarifai.com/openai/embed/models/text-embedding-ada\",\n",
+    "        }\n",
+    "}\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step-4: Add data sources to your app"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "app.add(\"https://www.forbes.com/profile/elon-musk\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step-5: All set. Now start asking questions related to your data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "while(True):\n",
+    "    question = input(\"Enter question: \")\n",
+    "    if question in ['q', 'exit', 'quit']:\n",
+    "        break\n",
+    "    answer = app.query(question)\n",
+    "    print(answer)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "v1",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.9.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

poetry.lock

@@ -854,6 +854,49 @@ typer = ">=0.9.0"
 typing-extensions = ">=4.5.0"
 uvicorn = {version = ">=0.18.3", extras = ["standard"]}
 
+[[package]]
+name = "clarifai"
+version = "10.3.2"
+description = "Clarifai Python SDK"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "clarifai-10.3.2-py3-none-any.whl", hash = "sha256:53a788af293875138a249af3334286799fa1e8dd0290e34c1da46fb522b5003e"},
+    {file = "clarifai-10.3.2.tar.gz", hash = "sha256:3ac864f67d8d294535ecaa79cbb3236ac1d8d2ff8c6319865f83c260cefa7f50"},
+]
+
+[package.dependencies]
+clarifai-grpc = ">=10.2.3,<10.3.0"
+inquirerpy = "0.3.4"
+numpy = ">=1.22.0"
+Pillow = ">=9.5.0"
+PyYAML = ">=6.0.1"
+rich = ">=13.4.2"
+schema = ">=0.7.5"
+tabulate = ">=0.9.0"
+tqdm = ">=4.65.0"
+tritonclient = ">=2.34.0"
+
+[package.extras]
+all = ["pycocotools (==2.0.6)"]
+
+[[package]]
+name = "clarifai-grpc"
+version = "10.2.3"
+description = "Clarifai gRPC API Client"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "clarifai-grpc-10.2.3.tar.gz", hash = "sha256:b03f87997a5ab2f810b046ad2a19c2d14260fa7bd4ce410d81c817f03e899202"},
+    {file = "clarifai_grpc-10.2.3-py3-none-any.whl", hash = "sha256:da24eb816ac93fa10cd5ec8114683ea7215ef31197e2601f92e88dc3a0566f43"},
+]
+
+[package.dependencies]
+googleapis-common-protos = ">=1.53.0"
+grpcio = ">=1.44.0"
+protobuf = ">=3.20.3"
+requests = ">=2.25.1"
+
 [[package]]
 name = "click"
 version = "8.1.7"
@@ -2574,6 +2617,24 @@ files = [
     {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
 ]
 
+[[package]]
+name = "inquirerpy"
+version = "0.3.4"
+description = "Python port of Inquirer.js (A collection of common interactive command-line user interfaces)"
+optional = true
+python-versions = ">=3.7,<4.0"
+files = [
+    {file = "InquirerPy-0.3.4-py3-none-any.whl", hash = "sha256:c65fdfbac1fa00e3ee4fb10679f4d3ed7a012abf4833910e63c295827fe2a7d4"},
+    {file = "InquirerPy-0.3.4.tar.gz", hash = "sha256:89d2ada0111f337483cb41ae31073108b2ec1e618a49d7110b0d7ade89fc197e"},
+]
+
+[package.dependencies]
+pfzy = ">=0.3.1,<0.4.0"
+prompt-toolkit = ">=3.0.1,<4.0.0"
+
+[package.extras]
+docs = ["Sphinx (>=4.1.2,<5.0.0)", "furo (>=2021.8.17-beta.43,<2022.0.0)", "myst-parser (>=0.15.1,<0.16.0)", "sphinx-autobuild (>=2021.3.14,<2022.0.0)", "sphinx-copybutton (>=0.4.0,<0.5.0)"]
+
 [[package]]
 name = "intel-openmp"
 version = "2021.4.0"
@@ -4300,6 +4361,20 @@ files = [
     {file = "pathspec-0.12.1.tar.gz", hash = "sha256:a482d51503a1ab33b1c67a6c3813a26953dbdc71c31dacaef9a838c4e29f5712"},
 ]
 
+[[package]]
+name = "pfzy"
+version = "0.3.4"
+description = "Python port of the fzy fuzzy string matching algorithm"
+optional = true
+python-versions = ">=3.7,<4.0"
+files = [
+    {file = "pfzy-0.3.4-py3-none-any.whl", hash = "sha256:5f50d5b2b3207fa72e7ec0ef08372ef652685470974a107d0d4999fc5a903a96"},
+    {file = "pfzy-0.3.4.tar.gz", hash = "sha256:717ea765dd10b63618e7298b2d98efd819e0b30cd5905c9707223dceeb94b3f1"},
+]
+
+[package.extras]
+docs = ["Sphinx (>=4.1.2,<5.0.0)", "furo (>=2021.8.17-beta.43,<2022.0.0)", "myst-parser (>=0.15.1,<0.16.0)", "sphinx-autobuild (>=2021.3.14,<2022.0.0)", "sphinx-copybutton (>=0.4.0,<0.5.0)"]
+
 [[package]]
 name = "pillow"
 version = "10.3.0"
@@ -4488,6 +4563,20 @@ nodeenv = ">=0.11.1"
 pyyaml = ">=5.1"
 virtualenv = ">=20.10.0"
 
+[[package]]
+name = "prompt-toolkit"
+version = "3.0.47"
+description = "Library for building powerful interactive command lines in Python"
+optional = true
+python-versions = ">=3.7.0"
+files = [
+    {file = "prompt_toolkit-3.0.47-py3-none-any.whl", hash = "sha256:0d7bfa67001d5e39d02c224b663abc33687405033a8c422d0d675a5a13361d10"},
+    {file = "prompt_toolkit-3.0.47.tar.gz", hash = "sha256:1e1b29cb58080b1e69f207c893a1a7bf16d127a5c30c9d17a25a5d77792e5360"},
+]
+
+[package.dependencies]
+wcwidth = "*"
+
 [[package]]
 name = "proto-plus"
 version = "1.23.0"
@@ -5227,6 +5316,88 @@ files = [
 [package.extras]
 cli = ["click (>=5.0)"]
 
+[[package]]
+name = "python-rapidjson"
+version = "1.17"
+description = "Python wrapper around rapidjson"
+optional = true
+python-versions = ">=3.6"
+files = [
+    {file = "python-rapidjson-1.17.tar.gz", hash = "sha256:95a111da29d996af8549f8b32ec701dab3af2ab7c6cd9c79540391ecb05f20c8"},
+    {file = "python_rapidjson-1.17-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:87d3d12c3d7436a7b43780b190d3e659d59c44b80d54c175c2837b399c4e7db9"},
+    {file = "python_rapidjson-1.17-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ac66ea04b450e8a9914a7de410a1d01a1011c11d5e72a3296a7d14e2636e3bd5"},
+    {file = "python_rapidjson-1.17-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:41747cf6284c7fa578bcc32e406b65351b084f4cb8d89d6bf631e5a86fd2fb92"},
+    {file = "python_rapidjson-1.17-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f942d0b73c9addef42683aa17a77f61075816592b799b825aa72573d073b3603"},
+    {file = "python_rapidjson-1.17-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c666f88c3d20a420a96561659a9cd38e79735d7dfbe603dfc612b545cd082f47"},
+    {file = "python_rapidjson-1.17-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:92766b71d8398dc132ad5b54654045dc05c1fb92ba674d83bdc694e476f67388"},
+    {file = "python_rapidjson-1.17-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:fde021615cb4fce0415ce9c168024b4801bac881084a72c6d8ae65fd1eb4b8e8"},
+    {file = "python_rapidjson-1.17-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:a0d1356c2816d31d3c8798363a9c92479e7aa1c9344d4cb48b7e396cd1dbe7dc"},
+    {file = "python_rapidjson-1.17-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:67d4645604f7ab95437d8a1fdd616c17e7100414224f139364a8a7b3b875a524"},
+    {file = "python_rapidjson-1.17-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:ee814bea835a9e8578f4bddc05cd55f92a54cad57d78fb00778d2d177bfd4862"},
+    {file = "python_rapidjson-1.17-cp310-cp310-win32.whl", hash = "sha256:29ff7c77eda1e95d5422a6778ff37e0a43ab769c7ff1e62e102557fafe729203"},
+    {file = "python_rapidjson-1.17-cp310-cp310-win_amd64.whl", hash = "sha256:2a947d825d1c4789f9b376fd3b602a037e3020546bfb8648a8128d94394a7fe0"},
+    {file = "python_rapidjson-1.17-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8cb8b38b4b4150082f9c97c65d5bb8b2dd748e1e9c05429247d629406385222b"},
+    {file = "python_rapidjson-1.17-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2ef881461db16a7e09273b8a3ea36777a0ac8405d5eec507c365f408dd657a22"},
+    {file = "python_rapidjson-1.17-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:701a301c540a911485a326857a7c16f8d048722bcd0cc2e1db2aa7008f35cfe3"},
+    {file = "python_rapidjson-1.17-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c0a4364238b2a193814073da7f825688cbf1cc77f9949452aaee5452c8f9e6f0"},
+    {file = "python_rapidjson-1.17-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e45146f8549a34d22e992eef1bde42e074ee24dfe0f5d2df5a74bb9632150765"},
+    {file = "python_rapidjson-1.17-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66e3b40012e22dd17d4390f3674320f461baba00f09666b8cc55d35a7860c382"},
+    {file = "python_rapidjson-1.17-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:be466029d473e23a9c3379c982b1350f411d783549e301495eb794b7f53a408d"},
+    {file = "python_rapidjson-1.17-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:f2fffa772a880897b9848b99ccd5e75aba82bffe50c898d6f611ae36b1c0cb78"},
+    {file = "python_rapidjson-1.17-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:df1ea407c57e607913c4c85d03cdc172b5cf742b87d6f8b13b54fc5163ffd804"},
+    {file = "python_rapidjson-1.17-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:1f6e91cb384189a0b74c5795448e0959ac84262d3c83815dc80f3749ab8812f5"},
+    {file = "python_rapidjson-1.17-cp311-cp311-win32.whl", hash = "sha256:e7c5a7c434f2ad928c3d51651f991204b9948fa495f585014fcdc413c353ec19"},
+    {file = "python_rapidjson-1.17-cp311-cp311-win_amd64.whl", hash = "sha256:14a57e8a13a9c92cef060766f76fe729af84b56450b32252786e864a3f2fed16"},
+    {file = "python_rapidjson-1.17-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d375bcc524a48078c791419343487e45c8a92c8c813229be8e12fb02c8902722"},
+    {file = "python_rapidjson-1.17-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:511a252122b61f9767c695a981753e45ca078cc4555a044d62eaf0fe6c6ef034"},
+    {file = "python_rapidjson-1.17-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9cf25006fc6752c0aafe5c3bdb9ff878531efd8a6aa3ac3e438d143ba2cc2b19"},
+    {file = "python_rapidjson-1.17-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2dc8701780f69493c1e57ac3c5ace8d36d84e01d06d5d03459b673afbf311b52"},
+    {file = "python_rapidjson-1.17-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:27e9c3d503eb43c6d899c2947148bde272fb04ba343226d98a34011c077edd35"},
+    {file = "python_rapidjson-1.17-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:efa33a296a103cc86dc187bde8eee7c416ca53fe904a68ad7cf75c7713ffa357"},
+    {file = "python_rapidjson-1.17-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:c72db2de40106486fb39eef565b65cd783a7a4a8020b8c15f3a34b23323e0e1f"},
+    {file = "python_rapidjson-1.17-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:849c74af38a049a6590b113256351e2b7143c586fd3024893c13fc5f48e6f961"},
+    {file = "python_rapidjson-1.17-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:70a4dcf2befaebd83d2df551c1c7162ac8d150e0065e94ac486907f7f05bd1b0"},
+    {file = "python_rapidjson-1.17-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b2f2ec6b960bc7b523e9a126da7c923c4a911d793f5942231adcc7b121ce4a05"},
+    {file = "python_rapidjson-1.17-cp312-cp312-win32.whl", hash = "sha256:2387690306a07afd9b2702ce90d5656d095caf49bbac726df38c586401df0606"},
+    {file = "python_rapidjson-1.17-cp312-cp312-win_amd64.whl", hash = "sha256:3e0ec69dad3cd0b0abdcc10865630ebcc016669a05b03aa79d25f596d1b22c44"},
+    {file = "python_rapidjson-1.17-cp313-cp313-macosx_10_9_x86_64.whl", hash = "sha256:fcf6b200eab700009a9d6eff961c58a6402eb729c9850a2e07da1437ba7a7a83"},
+    {file = "python_rapidjson-1.17-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:5e5e9070c38fc2c9700df85d97c9cf2731fd704531f42ed7bcedd1d46748d574"},
+    {file = "python_rapidjson-1.17-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:35fabf61d3c7f78b9dd852732576ab870bcb2d1caae7834d3622ef6fabfb4f1e"},
+    {file = "python_rapidjson-1.17-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bd5792883dbc715616ee4173ffe48ede4a824ecc58a9f31109afeec331b6830d"},
+    {file = "python_rapidjson-1.17-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44532140a00217f3949344136a3875903eaf7598a3671ad840aa001104639b42"},
+    {file = "python_rapidjson-1.17-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9aeda5f79ebc32cc38ec53af17b85d40c2c0330effa60ea564fc3f22b6ecfbc5"},
+    {file = "python_rapidjson-1.17-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:e214c8aeae862b529b304f96ffe91b93efb57e919f11c3cb875b02b0855f76e3"},
+    {file = "python_rapidjson-1.17-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:3f8bd5dc3a797450b84dfbc155553472d949ff721d16bde4bdf026758c88b260"},
+    {file = "python_rapidjson-1.17-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:2ae0a20d269b6207b225029952f6cbcc45d6fceba8f03e5035e5a5f3e7924e44"},
+    {file = "python_rapidjson-1.17-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:04bb97218061748ee4b630587c7ed668d65868a04c357b1069c1d7200c33da3e"},
+    {file = "python_rapidjson-1.17-cp313-cp313-win32.whl", hash = "sha256:a5e8779e1a53838957d6c185c6c6bb19578008c9bb48f2a735834cc538e26f1f"},
+    {file = "python_rapidjson-1.17-cp313-cp313-win_amd64.whl", hash = "sha256:2582d26621af8fe0e8dac8d739c2758d15aeae44958fbcf3b3120536c45b5a31"},
+    {file = "python_rapidjson-1.17-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b3110fefbf8ec4c5c66859ba3576040a44a1ff475db5034d34d6582e4762e4ce"},
+    {file = "python_rapidjson-1.17-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7b9f6aa56f24f8b527a18f2e4ab45946983d488f9eec83193432417b91086bb6"},
+    {file = "python_rapidjson-1.17-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:efa5f656addd3ccac264997f6e6c8fabd1555617248c47cd04d542f5b9a1a527"},
+    {file = "python_rapidjson-1.17-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:be4d2b47368af3b206d6c88bfd492e6cda6b4053b6900938bd2c2d81c007fc22"},
+    {file = "python_rapidjson-1.17-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d35662a224d2213d3078e8411aeb58f0d96eef9df7863b4fba62d7d665b73232"},
+    {file = "python_rapidjson-1.17-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e4b859d8eef65550cb191769bed4f6aed94fdf6262337c39695a3270e766e1d9"},
+    {file = "python_rapidjson-1.17-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:b98bcfcd81ca56adde1e80612378bf74dd46332f2f283c65dfee3f25ee149f3d"},
+    {file = "python_rapidjson-1.17-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:596189aa0462c42f5024f9aea5fffef5ca8c64e8eaff2436f0ec192a7ca6d902"},
+    {file = "python_rapidjson-1.17-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:84209abefba673f4f227a41c1d509e026a4dd68342495127bb0c6c1fe4e39107"},
+    {file = "python_rapidjson-1.17-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:6104a0c6d8ae6fb1aa06bd528829371ea93143f40c09ba38a90835808103c62b"},
+    {file = "python_rapidjson-1.17-cp38-cp38-win32.whl", hash = "sha256:77c9d9632010ab9c0d8f94da281cce6a5729c9d43b12a77b8ab0ef537df4b3f9"},
+    {file = "python_rapidjson-1.17-cp38-cp38-win_amd64.whl", hash = "sha256:e87fb60381d2df441aa60b3dac77df20f6044ed4fcfd92021cb139bf7280894c"},
+    {file = "python_rapidjson-1.17-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c59e5ab360b5765387607ec1b08c8a97a04e56fa73d3538775a81f2250a3d055"},
+    {file = "python_rapidjson-1.17-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:fb7015de6d08d7cc37485e031ae7b99377971dd1b4ebcc8027d71b8094cb5921"},
+    {file = "python_rapidjson-1.17-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c4b6fc4b185c5096092ca4a595bf272d3eb77c557c9c194cd5d5b1d677e164c7"},
+    {file = "python_rapidjson-1.17-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fa32abeeeae7d1559f4a17d4c009f6f42c9dd90275a6bc8febc59c21cf6e0ef8"},
+    {file = "python_rapidjson-1.17-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e101a79b606ae9f89c6d15ffb32b61481b1e6188591821bef18380c813fa921b"},
+    {file = "python_rapidjson-1.17-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2531ff943ad7ccc3381dbf54b453a9f6a479caac7c7c47678322cac0253bf045"},
+    {file = "python_rapidjson-1.17-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:328a052da424d7f0a4986160df623eb7d189c0b5e1bf533ec0e50cc85642aa71"},
+    {file = "python_rapidjson-1.17-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:958ecbd226da221059ca3a9a0320d88ac11980bfaac222ab7254a6c4673bfd46"},
+    {file = "python_rapidjson-1.17-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:0e3dd0361d1f0594617092b303754b43a4b9d75d47b16eb3282aa97c3eab44f7"},
+    {file = "python_rapidjson-1.17-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:6f910c7284a38becf30896fef7a59c88c840379d4f082d7283b065a2b398f641"},
+    {file = "python_rapidjson-1.17-cp39-cp39-win32.whl", hash = "sha256:3f686eb5d68b2775f60641a1c07c3329db7e7b3a6e5c1a7d4907078699c8396f"},
+    {file = "python_rapidjson-1.17-cp39-cp39-win_amd64.whl", hash = "sha256:df64031b785dee4b72d3cd8ce4cfcef46982d6c580182b0086d7ebc038be3b63"},
+]
+
 [[package]]
 name = "pytube"
 version = "15.0.0"
@@ -6675,6 +6846,28 @@ build = ["cmake (>=3.20)", "lit"]
 tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"]
 tutorials = ["matplotlib", "pandas", "tabulate", "torch"]
 
+[[package]]
+name = "tritonclient"
+version = "2.41.1"
+description = "Python client library and utilities for communicating with Triton Inference Server"
+optional = true
+python-versions = "*"
+files = [
+    {file = "tritonclient-2.41.1-py3-none-any.whl", hash = "sha256:91cb234331a7145c407cea605caf9eecbd4276ddc5f085ddd5a6dcab64e5e70b"},
+    {file = "tritonclient-2.41.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:22ad56ae5ab25518862dec85af0a8246a32a1e14e2ee1d86f1444ce432c254e1"},
+    {file = "tritonclient-2.41.1-py3-none-manylinux2014_aarch64.whl", hash = "sha256:6545055add115e9bd07ca540af95db5ceda0c783009ad41df6a7f35a79d57474"},
+]
+
+[package.dependencies]
+numpy = ">=1.19.1"
+python-rapidjson = ">=0.9.1"
+
+[package.extras]
+all = ["aiohttp (>=3.8.1,<4.0.0)", "cuda-python", "geventhttpclient (>=1.4.4,<=2.0.2)", "grpcio (>=1.41.0)", "numpy (>=1.19.1)", "packaging (>=14.1)", "protobuf (>=3.5.0,<5)", "python-rapidjson (>=0.9.1)"]
+cuda = ["cuda-python"]
+grpc = ["grpcio (>=1.41.0)", "numpy (>=1.19.1)", "packaging (>=14.1)", "protobuf (>=3.5.0,<5)", "python-rapidjson (>=0.9.1)"]
+http = ["aiohttp (>=3.8.1,<4.0.0)", "geventhttpclient (>=1.4.4,<=2.0.2)", "numpy (>=1.19.1)", "python-rapidjson (>=0.9.1)"]
+
 [[package]]
 name = "twilio"
 version = "8.13.0"
@@ -7121,6 +7314,17 @@ files = [
 [package.dependencies]
 anyio = ">=3.0.0"
 
+[[package]]
+name = "wcwidth"
+version = "0.2.13"
+description = "Measures the displayed width of unicode strings in a terminal"
+optional = true
+python-versions = "*"
+files = [
+    {file = "wcwidth-0.2.13-py2.py3-none-any.whl", hash = "sha256:3da69048e4540d84af32131829ff948f1e022c1c6bdb8d6102117aac784f6859"},
+    {file = "wcwidth-0.2.13.tar.gz", hash = "sha256:72ea0c06399eb286d978fdedb6923a9eb47e1c486ce63e9b4e64fc18303972b5"},
+]
+
 [[package]]
 name = "weaviate-client"
 version = "3.26.2"
@@ -7520,4 +7724,4 @@ youtube = ["youtube-transcript-api", "yt_dlp"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<=3.13"
-content-hash = "c63e9ce659b1148ca8685bbd81ac65adc07d8cc75abe28856525f6a247ce7856"
+content-hash = "757481b96e9620d643c4ef77131c295ad22541784d5c6395d2c6da366d7ae7d3"

pyproject.toml

@@ -119,6 +119,7 @@ twilio = { version = "^8.5.0", optional = true }
 fastapi-poe = { version = "0.0.16", optional = true }
 discord = { version = "^2.3.2", optional = true }
 slack-sdk = { version = "3.21.3", optional = true }
+clarifai = { version = "^10.0.1", optional = true }
 cohere = { version = "^5.3", optional = true }
 together = { version = "^0.2.8", optional = true }
 weaviate-client = { version = "^3.24.1", optional = true }

tests/llm/test_clarifai.py

@@ -0,0 +1,23 @@
+
+import pytest
+
+from embedchain.config import BaseLlmConfig
+from embedchain.llm.clarifai import ClarifaiLlm
+
+
+@pytest.fixture
+def clarifai_llm_config(monkeypatch):
+    monkeypatch.setenv("CLARIFAI_PAT","test_api_key")
+    config = BaseLlmConfig(
+        model="https://clarifai.com/openai/chat-completion/models/GPT-4",
+        model_kwargs={"temperature": 0.7, "max_tokens": 100},
+    )
+    yield config
+    monkeypatch.delenv("CLARIFAI_PAT")
+
+def test_clarifai__llm_get_llm_model_answer(clarifai_llm_config, mocker):
+    mocker.patch("embedchain.llm.clarifai.ClarifaiLlm._get_answer", return_value="Test answer")
+    llm = ClarifaiLlm(clarifai_llm_config)
+    answer = llm.get_llm_model_answer("Test query")
+
+    assert answer == "Test answer"