my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: '❓ query'
#3	---
#4
#5	`.query()` method empowers developers to ask questions and receive relevant answers through a user-friendly query API. Function signature is given below:
#6
#7	### Parameters
#8
#9	<ParamField path="input_query" type="str">
#10	Question to ask
#11	</ParamField>
#12	<ParamField path="config" type="BaseLlmConfig" optional>
#13	Configure different llm settings such as prompt, temprature, number_documents etc.
#14	</ParamField>
#15	<ParamField path="dry_run" type="bool" optional>
#16	The purpose is to test the prompt structure without actually running LLM inference. Defaults to `False`
#17	</ParamField>
#18	<ParamField path="where" type="dict" optional>
#19	A dictionary of key-value pairs to filter the chunks from the vector database. Defaults to `None`
#20	</ParamField>
#21	<ParamField path="citations" type="bool" optional>
#22	Return citations along with the LLM answer. Defaults to `False`
#23	</ParamField>
#24
#25	### Returns
#26
#27	<ResponseField name="answer" type="str \| tuple">
#28	If `citations=False`, return a stringified answer to the question asked. <br />
#29	If `citations=True`, returns a tuple with answer and citations respectively.
#30	</ResponseField>
#31
#32	## Usage
#33
#34	### With citations
#35
#36	If you want to get the answer to question and return both answer and citations, use the following code snippet:
#37
#38	```python With Citations
#39	from embedchain import App
#40
#41	# Initialize app
#42	app = App()
#43
#44	# Add data source
#45	app.add("https://www.forbes.com/profile/elon-musk")
#46
#47	# Get relevant answer for your query
#48	answer, sources = app.query("What is the net worth of Elon?", citations=True)
#49	print(answer)
#50	# Answer: The net worth of Elon Musk is $221.9 billion.
#51
#52	print(sources)
#53	# [
#54	# (
#55	# 'Elon Musk PROFILEElon MuskCEO, Tesla$247.1B$2.3B (0.96%)Real Time Net Worthas of 12/7/23 ...',
#56	# {
#57	# 'url': 'https://www.forbes.com/profile/elon-musk',
#58	# 'score': 0.89,
#59	# ...
#60	# }
#61	# ),
#62	# (
#63	# '74% of the company, which is now called X.Wealth HistoryHOVER TO REVEAL NET WORTH BY YEARForbes ...',
#64	# {
#65	# 'url': 'https://www.forbes.com/profile/elon-musk',
#66	# 'score': 0.81,
#67	# ...
#68	# }
#69	# ),
#70	# (
#71	# 'founded in 2002, is worth nearly $150 billion after a $750 million tender offer in June 2023 ...',
#72	# {
#73	# 'url': 'https://www.forbes.com/profile/elon-musk',
#74	# 'score': 0.73,
#75	# ...
#76	# }
#77	# )
#78	# ]
#79	```
#80
#81	<Note>
#82	When `citations=True`, note that the returned `sources` are a list of tuples where each tuple has two elements (in the following order):
#83	1. source chunk
#84	2. dictionary with metadata about the source chunk
#85	- `url`: url of the source
#86	- `doc_id`: document id (used for book keeping purposes)
#87	- `score`: score of the source chunk with respect to the question
#88	- other metadata you might have added at the time of adding the source
#89	</Note>
#90
#91	### Without citations
#92
#93	If you just want to return answers and don't want to return citations, you can use the following example:
#94
#95	```python Without Citations
#96	from embedchain import App
#97
#98	# Initialize app
#99	app = App()
#100
#101	# Add data source
#102	app.add("https://www.forbes.com/profile/elon-musk")
#103
#104	# Get relevant answer for your query
#105	answer = app.query("What is the net worth of Elon?")
#106	print(answer)
#107	# Answer: The net worth of Elon Musk is $221.9 billion.
#108	```
#109
#110

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public