my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	{
#2	"cells": [
#3	{
#4	"cell_type": "markdown",
#5	"metadata": {},
#6	"source": [
#7	"# Cookbook for using Clarifai LLM and Embedders with Embedchain"
#8	]
#9	},
#10	{
#11	"cell_type": "markdown",
#12	"metadata": {},
#13	"source": [
#14	"## Step-1: Install embedchain-clarifai package"
#15	]
#16	},
#17	{
#18	"cell_type": "code",
#19	"execution_count": null,
#20	"metadata": {},
#21	"outputs": [],
#22	"source": [
#23	"!pip install embedchain[clarifai]"
#24	]
#25	},
#26	{
#27	"cell_type": "markdown",
#28	"metadata": {},
#29	"source": [
#30	"## Step-2: Set Clarifai PAT as env variable.\n",
#31	"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",
#32	"\n",
#33	"optionally you can also pass `api_key` in config of llm/embedder class."
#34	]
#35	},
#36	{
#37	"cell_type": "code",
#38	"execution_count": null,
#39	"metadata": {},
#40	"outputs": [],
#41	"source": [
#42	"import os\n",
#43	"from embedchain import App\n",
#44	"\n",
#45	"os.environ[\"CLARIFAI_PAT\"]=\"xxx\""
#46	]
#47	},
#48	{
#49	"cell_type": "markdown",
#50	"metadata": {},
#51	"source": [
#52	"## Step-3 Create embedchain app using clarifai LLM and embedder and define your config.\n",
#53	"\n",
#54	"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."
#55	]
#56	},
#57	{
#58	"cell_type": "code",
#59	"execution_count": null,
#60	"metadata": {},
#61	"outputs": [],
#62	"source": [
#63	"# Use model_kwargs to pass all model specific parameters for inference.\n",
#64	"app = App.from_config(config={\n",
#65	" \"llm\": {\n",
#66	" \"provider\": \"clarifai\",\n",
#67	" \"config\": {\n",
#68	" \"model\": \"https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct\",\n",
#69	" \"model_kwargs\": {\n",
#70	" \"temperature\": 0.5,\n",
#71	" \"max_tokens\": 1000\n",
#72	" }\n",
#73	" }\n",
#74	" },\n",
#75	" \"embedder\": {\n",
#76	" \"provider\": \"clarifai\",\n",
#77	" \"config\": {\n",
#78	" \"model\": \"https://clarifai.com/openai/embed/models/text-embedding-ada\",\n",
#79	" }\n",
#80	"}\n",
#81	"})"
#82	]
#83	},
#84	{
#85	"cell_type": "markdown",
#86	"metadata": {},
#87	"source": [
#88	"## Step-4: Add data sources to your app"
#89	]
#90	},
#91	{
#92	"cell_type": "code",
#93	"execution_count": null,
#94	"metadata": {},
#95	"outputs": [],
#96	"source": [
#97	"app.add(\"https://www.forbes.com/profile/elon-musk\")"
#98	]
#99	},
#100	{
#101	"cell_type": "markdown",
#102	"metadata": {},
#103	"source": [
#104	"## Step-5: All set. Now start asking questions related to your data"
#105	]
#106	},
#107	{
#108	"cell_type": "code",
#109	"execution_count": null,
#110	"metadata": {},
#111	"outputs": [],
#112	"source": [
#113	"while(True):\n",
#114	" question = input(\"Enter question: \")\n",
#115	" if question in ['q', 'exit', 'quit']:\n",
#116	" break\n",
#117	" answer = app.query(question)\n",
#118	" print(answer)"
#119	]
#120	}
#121	],
#122	"metadata": {
#123	"kernelspec": {
#124	"display_name": "v1",
#125	"language": "python",
#126	"name": "python3"
#127	},
#128	"language_info": {
#129	"name": "python",
#130	"version": "3.9.10"
#131	}
#132	},
#133	"nbformat": 4,
#134	"nbformat_minor": 2
#135	}
#136

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public