Build ‘Agents’ that search web, does math and write python with Mixtral 8x-7B, Langchain and Groq.
Introduction
In the realm of cutting-edge technology, Langchain agents stand out as versatile and powerful tools, offering a myriad of applications across various domains. In this blog, we’ll delve into the fundamentals of Langchain agents, exploring what they are, how they operate, and why they are indispensable in today’s technological landscape. Additionally, we’ll highlight the utilization of Mistral 8x-7B, an exceptional open-source model, in the development and implementation of these agents.
Lets understand agents {quick summary} -
What are they?
How do they work?
Why do we need them?
What are Agents?
Agents are like digital helpers that can think for themselves (well, sort of!). They’re designed to tackle tasks and make decisions, but in a virtual world. Instead of following a fixed set of rules like a robot, agents use LLM to derive certain sequence of activities {which is termed as reasoning} — to determine which actions to take and in which order.
For example- When a question is framed infront of the LLM it tries to answer this with the data it has been trained on. In agents the concept is same {LLM will respond} but the order of actions will define the answer.
How Do They Work?
Agents function through a series of steps that involve passing information to the Language Model (LM) and receiving responses. Let’s break it down with an example:
Imagine you’re asking a question about cars. Initially, you might just ask, “What is a car?” But as you refine your query with specific roles or goals, the LM’s responses adapt accordingly:
- Basic Question: “What is a car?”
- Question with Role: “As a Research Analyst, what is a car?”
- Question with Role and Goal: “As a Research Analyst, tasked with providing market analysis, what is a car?”
- Question with Role, Goal, and Backstory: “As a Research Analyst, with expertise in market trends, what is a car?”
These prompts showcase how the LM’s responses evolve based on the context provided.
Now, let’s explore this process further with three hypothetical agents:
- Agent Math: Handles mathematical questions.
- Agent Web: Browses the internet.
- Agent Wikipedia: Fact-checks information.
When you ask a question, the LM responds using its pre-existing knowledge. However, this might not always provide the exact answer you’re looking for.
Within the agents framework:
- Question Breakdown: The LM breaks down your question into actions.
- Action Assignment: These actions are then assigned to the appropriate agents, determined by the LM.
- Agent Action: Each agent, equipped with its specific functions, carries out its assigned task.
- Evaluation: The results from the agents are collected on a scratch pad for the LM to review.
- Response Generation: Finally, the LM synthesizes the information gathered from the agents to generate a comprehensive response.
In essence, agents facilitate a dynamic exchange where questions are parsed, actions are executed, and responses are synthesized, all orchestrated by the LM to provide tailored and relevant information.
Why do we need them?
We need retrievers to process information and get to the correct answers.
Prompting Techniques - Here you can ask questions to LLM and evaluate the LLM response based on the pre-training data. Here the scope to get the correct answer is very low. These are out of box model and can only generate back the data it is trained on.
Finetuing your LLM - One of the approach to retrieve correct answers, is Fine tuning you LLM on curated data. In this approach we have to create a dataset. Also we have come up with a fine tuning strategty like SFT, QLoRa, DPO. {My humble request,please go through the research papers}
Naive/Advanced RAG - With Vector db,SQL DB and NoSql, we try to retrieve information from these data sources.
Either we get the query created by LLM and execute on sql to retrive results or we create a vector db for text data to do similarity search for the documents.
Agents — Imagine agents as smart helpers with specific roles, goals, and a memory of past interactions {conversational}. They break down all the information they receive into smaller, actionable tasks. These tasks trigger specific functions to work on them, retrieving necessary information. Once these tasks are completed, the Language and Logic Model (LLM) steps in to compile all the gathered information and craft a final answer.
In essence, agents are like organized assistants who process information, perform tasks, and then use their intelligence to give you the best possible answer.
Lets build it with langchain and Mistral 8x-7B & Groq
Groq provides good inference at very low cost/prices. As of now they are providing API access for free for 10 days.
!pip install langchain-groq #langchain module
from langchain_core.prompts import ChatPromptTemplate
from langchain_groq import ChatGroq
llm = ChatGroq(temperature=0.5, #If the temperature is set to a lower value, the model tends to produce more deterministic response
groq_api_key="your-groq-key",
model_name="mixtral-8x7b-32768",
max_tokens=20000) #Mistral context window is 32768 tokens, however we are limiting that to 20K tokens.Let’s explore how these functions operate independently. To start, we’ll examine the Wikipedia API. In simpler terms, we’ll take a look at how each of these processes works on its own.
from langchain.utilities import WikipediaAPIWrapper
wikipedia = WikipediaAPIWrapper()
wikipedia.run('Langchain')PythonREPL is a convenient way to prototype ideas, debug code, or quickly verify syntax. Whether you’re debugging a tricky algorithm or exploring the behavior of a specific Python module, PythonREPL gives you the flexibility to experiment and iterate rapidly
from langchain.utilities import PythonREPL
python_repl = PythonREPL()
python_repl.run("print(17*2)")'34\n'DuckDuck Go API offers a convenient way to browse the web and obtain quick responses on demand. It’s like having a search engine at your fingertips wherever you go.
Alternatively, SerpAPI and Brave API are also effective options, but they often come with costs and certain restrictions. These alternatives provide similar functionalities, but users may need to consider factors like pricing and usage limits before making a choice.
from langchain.tools import DuckDuckGoSearchRun
search = DuckDuckGoSearchRun()
search.run("what is bitcoin price for today in INR?")## Response
Bitcoin INR Bitcoin to Indian Rupee Data The BTC to INR conversion rate today is ₹4,616,107.90 and has increased by 8.17% in the last 24 hours.
Our converter updates in real time giving you accurate data every time you use it to make a conversion.
The current price direction of Bitcoin is increasing because BTC is up 32.27% in the last 30 days.
BTC/INR: Convert Bitcoin (BTC) to Indian Rupee (INR) 1 Bitcoin equals ₹4,546,842.15 Indian Rupee Buy Bitcoin BTC Last update: 5:39 PM, February 26, 2024 Refresh Bitcoin Markets Bitcoin is climbing this week.
The current price of Bitcoin is ₹4,546,842.15 per BTC. INR Last update: 9:15 PM, February 26, 2024 Refresh Bitcoin Markets Bitcoin is climbing this week.
The current price of Bitcoin is ₹4,630,611.03 per BTC. With a circulating supply of 19,638,837 BTC, it means that Bitcoin has a total market cap of ₹90,868,629,233,432.38.
Bitcoin Price Index (XBX) Ether Price Index (ETX) Basic Attention Token Price Index (BTX) ...
Convert BTC to INR: Bitcoin to India Rupee. To FIAT. To Crypto. 1 Bitcoin equals India Rupee. BTC. INR.
The live price of Bitcoin is $ 51,066.09 per (BTC / USD) with a current market cap of $ 1,002.63B USD. 24-hour trading volume is $ 28.74B USD. BTC to USD price is updated in real-time.
Bitcoin is -0.41% in the last 24 hours with a circulating supply of 19.63M. BTC Price History USD BTC Price Information 24h Low & High Low: $ 50,773.21Having understood the mechanics of each function independently, let’s now merge them together and observe the outcomes.
from langchain.agents import Tool
tools = [
Tool(
name = "python repl",
func=python_repl.run,
description="useful for when you need to use python to answer a question. You should input python code"
)
]Let’s establish a clear definition for these tools to integrate them into the Agent framework.
wikipedia_tool = Tool(
name='wikipedia',
func= wikipedia.run,
description="Useful for when you need to look up a topic, country or person on wikipedia is the best website for fact check and any other details on any subject."
)
duckduckgo_tool = Tool(
name='DuckDuckGo Search',
func= search.run,
description="Useful for when you need to do a search on the internet to find information that another tool can't find. Always be specific with your input."
)Lets define math tool, Here, an instance of the LLMMathChain class is created, with llm being passed as a parameter. This suggests that llm_math is an object representing a mathematical chain within the LangChain framework.
from langchain.chains import LLMMathChain
from langchain.agents import Tool
llm_math = LLMMathChain(llm=llm)
# initialize the math tool
math_tool = Tool(
name='Calculator',
func=llm_math.run,
description='Useful for when you need to answer questions about math. Or you want to calculate something.'
)
Appending all the individuals functions to create one big tool
tools.append(duckduckgo_tool)
tools.append(wikipedia_tool)
tools.append(math_tool)Initializing Agent type, there are various agent types and you can choose them as per your requirements. For
“zero-shot-react-description” agents can perform zero-shot tasks on an input, meaning the agent only considers the current interaction and has no memory. This agent type is optimized for chat models and can invoke tools that have multiple inputs. It’s different from other agent types, such as conversational ReAct agents, which have memory to remember previous conversation interactions
from langchain.agents import initialize_agent
zero_shot_agent = initialize_agent(
agent="zero-shot-react-description",
tools=tools,
llm=llm,
verbose=True,
max_iterations=10,
)Initializing functon call
final_response = zero_shot_agent.run("Give me the best cars between a range of 40-60 lakhs in india.\
Also tell me how pricy other cars are. calculate the difference\
Also give me the working links about the information.\
I want minimum three links, one for text, one for video, and one for images")Intermediate Response
## Intermediate Response
> Entering new AgentExecutor chain...
This question involves finding the best cars in a certain price range in India, comparing their prices, and finding relevant links with different types of media. I will use a combination of DuckDuckGo Search and Wikipedia to find the information.
Action: DuckDuckGo Search
Action Input: "best cars in india between 40-60 lakhs"
Observation: The price for the best cars under 50 Lakh in India are: Toyota Fortuner price is Rs. 33.43 Lakh, Mercedes-Benz A-Class Limousine price is Rs. 42.8 Lakh, BMW X1 price is Rs. 49.5 Lakh and MINI ... With its impressive off-road capabilities, the new Toyota Fortuner is an ideal choice for adventure seekers and off-road enthusiasts, making it one of the best SUVs under 40 lakh in India. Engine capacity: 2.8-litre diesel/2.7-litre petrol engine. 2. Jeep Meridian. This is a curated list of the best cars under 40 lakhs in India. The list includes all body styles such as MPVs, SUVs, sedans and even pickups like the Toyota Hilux ... Rs 33.60 - 39.66 lakh. BYD Atto 3. Mid-size electric SUV. Rs 33.99 - 34.49 lakh. Citroen C5 Aircross. Mid-size SUV. Rs 36.91 - 37.67 lakh. MG Gloster. Full-size SUV. Hyundai Tucson. Introducing the Hyundai Tucson, a stylish and versatile SUV that offers a delightful combination of modern design and a commanding presence on the road. With a starting price of Rs. 28.63 Lakh and going up to Rs. 35.46 Lakh (Avg. ex-showroom), the Tucson is available in 8 variants to suit your preferences. Coupled with the zippy DCT transmission option, the Skoda Kushaq clocks 0-100 kmph in a mere 8.6 seconds. The three drive modes - normal, eco, and sport further amplify the overall driving experience. Adding to that, the Kushaq is one of the safest cars in India, with a commendable 5-star Global NCAP rating.
Thought:It seems like the search result provides a list of some of the best cars in India within the price range of 40-60 lakhs. However, the user also asked for a comparison of prices and the difference between these cars and others. To answer this question accurately, I need to gather more specific information about the prices of each car and calculate the difference.
Action: DuckDuckGo Search
Action Input: "prices of cars in india 40-60 lakhs"
Observation: ₹46.40 Lakh: BMW 3 Series: Petrol: Sedan: 15.3 - 16.3 km/l ₹43.60 Lakh - ₹53.90 Lakh ... Depending on the variant and customization options picked, the price of the Audi A6 in India ranges from about ₹60 lakhs to ₹68 lakhs. Key Specifications. Key Specifications: Details: Maximum Power ... Best 10 Made In India Cars - Price ... With its impressive off-road capabilities, the new Toyota Fortuner is an ideal choice for adventure seekers and off-road enthusiasts, making it one of the best SUVs under 40 lakh in India. Engine capacity: 2.8-litre diesel/2.7-litre petrol engine. 2. Jeep Meridian. The price for the best cars under 50 Lakh in India are: Toyota Fortuner price is Rs. 33.43 Lakh, Mercedes-Benz A-Class Limousine price is Rs. 42.8 Lakh, BMW X1 price is Rs. 49.5 Lakh and MINI ... Check List of New Cars in India 2022 New Car Brands New SUVs and Sedans Cars in India. ... New Kia cars in India 14. Kia Carens (Price: Rs. 9.60 lakh to Rs. 16.60 lakh) The Kia Carens is a Multi Utility Vehicle (MUV) with a SUVish design approach. ... (Price: Rs. 37.50 lakh to Rs. 40 lakh) The Skoda Kodiaq is a full-size SUV and looks premium ... This is a curated list of the best cars under 40 lakhs in India. The list includes all body styles such as MPVs, SUVs, sedans and even pickups like the Toyota Hilux ... Rs 33.60 - 39.66 lakh. BYD Atto 3. Mid-size electric SUV. Rs 33.99 - 34.49 lakh. ... most variants are available under this price point. Also, under 40 lakh you can own high ...
Thought:I now have a better understanding of the prices of cars in the 40-60 lakh price range in India. I can start comparing the prices of the cars mentioned earlier and calculate the difference.
Action: Calculator
Action Input: 5390000 - 4280000
Observation: Answer: 1110000
Thought:The price difference between the most expensive car mentioned (Audi A6 with a price of 53.90 lakhs) and the second most expensive one (Mercedes-Benz A-Class Limousine with a price of 42.8 lakhs) is 11.10 lakhs.
Thought: I have answered the user's question about the price difference between the two most expensive cars in the list. However, I still need to provide the user with information about the prices and features of other cars in this price range.
Final Answer: The prices of some of the best cars in India within the price range of 40-60 lakhs are as follows: Toyota Fortuner (33.43 lakhs), Mercedes-Benz A-Class Limousine (42.8 lakhs), BMW X1 (49.5 lakhs), Audi A6 (53.9 lakhs), and MINI (prices not mentioned). The price difference between the two most expensive cars mentioned (Audi A6 and Mercedes-Benz A-Class Limousine) is 11.10 lakhs.
Regarding the user's request for links, here are some relevant ones:
* Text link: <https://www.carwale.com/best-cars-under-50-lakhs-in-india/>
* Video link: <https://www.youtube.com/watch?v=3vxvgCZ1o-Y>
* Image link: <https://www.google.com/search?q=best+cars+under+50+lakhs+in+india&rlz=1C1GCEU_enIN836IN836&source=lnms&tbm=isch&sa=X&ved=0ahUKEwiB9Z6E5rX3AhXQg3MBHQz-CWQQ_AUIDCgD>
> Finished chain.Final Response
# Final Response
The prices of some of the best cars in India within the price range of 40-60 lakhs are as follows:
Toyota Fortuner (33.43 lakhs),
Mercedes-Benz A-Class Limousine (42.8 lakhs),
BMW X1 (49.5 lakhs),
Audi A6 (53.9 lakhs),
and MINI (prices not mentioned).
The price difference between the two most expensive cars mentioned (Audi A6 and Mercedes-Benz A-Class Limousine) is 11.10 lakhs.
Regarding the user's request for links, here are some relevant ones:
Text link: <https://www.carwale.com/best-cars-under-50-lakhs-in-india/>
Video link: <https://www.youtube.com/watch?v=3vxvgCZ1o-Y>
Image link: <https://www.google.com/search?q=best+cars+under+50+lakhs+in+india&rlz=1C1GCEU_enIN836IN836&source=lnms&tbm=isch&sa=X&ved=0ahUKEwiB9Z6E5rX3AhXQg3MBHQz-CWQQ_AUIDCgD>Next time we will build an Agent that will do RAG and self rectify the responses for better accuracy.
Please share your thoughts, comments and do support me so that I can bring such articles to you apart from my work projects.
