my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: ❓ FAQs
#3	description: 'Collections of all the frequently asked questions'
#4	---
#5	<AccordionGroup>
#6	<Accordion title="Does Embedchain support OpenAI's Assistant APIs?">
#7	Yes, it does. Please refer to the [OpenAI Assistant docs page](/examples/openai-assistant).
#8	</Accordion>
#9	<Accordion title="How to use MistralAI language model?">
#10	Use the model provided on huggingface: `mistralai/Mistral-7B-v0.1`
#11	<CodeGroup>
#12	```python main.py
#13	import os
#14	from embedchain import App
#15
#16	os.environ["HUGGINGFACE_ACCESS_TOKEN"] = "hf_your_token"
#17
#18	app = App.from_config("huggingface.yaml")
#19	```
#20	```yaml huggingface.yaml
#21	llm:
#22	provider: huggingface
#23	config:
#24	model: 'mistralai/Mistral-7B-v0.1'
#25	temperature: 0.5
#26	max_tokens: 1000
#27	top_p: 0.5
#28	stream: false
#29
#30	embedder:
#31	provider: huggingface
#32	config:
#33	model: 'sentence-transformers/all-mpnet-base-v2'
#34	```
#35	</CodeGroup>
#36	</Accordion>
#37	<Accordion title="How to use ChatGPT 4 turbo model released on OpenAI DevDay?">
#38	Use the model `gpt-4-turbo` provided my openai.
#39	<CodeGroup>
#40
#41	```python main.py
#42	import os
#43	from embedchain import App
#44
#45	os.environ['OPENAI_API_KEY'] = 'xxx'
#46
#47	# load llm configuration from gpt4_turbo.yaml file
#48	app = App.from_config(config_path="gpt4_turbo.yaml")
#49	```
#50
#51	```yaml gpt4_turbo.yaml
#52	llm:
#53	provider: openai
#54	config:
#55	model: 'gpt-4-turbo'
#56	temperature: 0.5
#57	max_tokens: 1000
#58	top_p: 1
#59	stream: false
#60	```
#61	</CodeGroup>
#62	</Accordion>
#63	<Accordion title="How to use GPT-4 as the LLM model?">
#64	<CodeGroup>
#65
#66	```python main.py
#67	import os
#68	from embedchain import App
#69
#70	os.environ['OPENAI_API_KEY'] = 'xxx'
#71
#72	# load llm configuration from gpt4.yaml file
#73	app = App.from_config(config_path="gpt4.yaml")
#74	```
#75
#76	```yaml gpt4.yaml
#77	llm:
#78	provider: openai
#79	config:
#80	model: 'gpt-4'
#81	temperature: 0.5
#82	max_tokens: 1000
#83	top_p: 1
#84	stream: false
#85	```
#86
#87	</CodeGroup>
#88	</Accordion>
#89	<Accordion title="I don't have OpenAI credits. How can I use some open source model?">
#90	<CodeGroup>
#91
#92	```python main.py
#93	from embedchain import App
#94
#95	# load llm configuration from opensource.yaml file
#96	app = App.from_config(config_path="opensource.yaml")
#97	```
#98
#99	```yaml opensource.yaml
#100	llm:
#101	provider: gpt4all
#102	config:
#103	model: 'orca-mini-3b-gguf2-q4_0.gguf'
#104	temperature: 0.5
#105	max_tokens: 1000
#106	top_p: 1
#107	stream: false
#108
#109	embedder:
#110	provider: gpt4all
#111	config:
#112	model: 'all-MiniLM-L6-v2'
#113	```
#114	</CodeGroup>
#115
#116	</Accordion>
#117	<Accordion title="How to stream response while using OpenAI model in Embedchain?">
#118	You can achieve this by setting `stream` to `true` in the config file.
#119
#120	<CodeGroup>
#121	```yaml openai.yaml
#122	llm:
#123	provider: openai
#124	config:
#125	model: 'gpt-4o-mini'
#126	temperature: 0.5
#127	max_tokens: 1000
#128	top_p: 1
#129	stream: true
#130	```
#131
#132	```python main.py
#133	import os
#134	from embedchain import App
#135
#136	os.environ['OPENAI_API_KEY'] = 'sk-xxx'
#137
#138	app = App.from_config(config_path="openai.yaml")
#139
#140	app.add("https://www.forbes.com/profile/elon-musk")
#141
#142	response = app.query("What is the net worth of Elon Musk?")
#143	# response will be streamed in stdout as it is generated.
#144	```
#145	</CodeGroup>
#146	</Accordion>
#147
#148	<Accordion title="How to persist data across multiple app sessions?">
#149	Set up the app by adding an `id` in the config file. This keeps the data for future use. You can include this `id` in the yaml config or input it directly in `config` dict.
#150	```python app1.py
#151	import os
#152	from embedchain import App
#153
#154	os.environ['OPENAI_API_KEY'] = 'sk-xxx'
#155
#156	app1 = App.from_config(config={
#157	"app": {
#158	"config": {
#159	"id": "your-app-id",
#160	}
#161	}
#162	})
#163
#164	app1.add("https://www.forbes.com/profile/elon-musk")
#165
#166	response = app1.query("What is the net worth of Elon Musk?")
#167	```
#168	```python app2.py
#169	import os
#170	from embedchain import App
#171
#172	os.environ['OPENAI_API_KEY'] = 'sk-xxx'
#173
#174	app2 = App.from_config(config={
#175	"app": {
#176	"config": {
#177	# this will persist and load data from app1 session
#178	"id": "your-app-id",
#179	}
#180	}
#181	})
#182
#183	response = app2.query("What is the net worth of Elon Musk?")
#184	```
#185	</Accordion>
#186	</AccordionGroup>
#187
#188	#### Still have questions?
#189	If docs aren't sufficient, please feel free to reach out to us using one of the following methods:
#190
#191	<Snippet file="get-help.mdx" />
#192

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public