Initially, when ChatGPT simply appeared, we used easy prompts to get solutions to our questions. Then, we encountered points with hallucinations and commenced utilizing RAG (Retrieval Augmented Era) to supply extra context to LLMs. After that, we began experimenting with AI brokers, the place LLMs act as a reasoning engine and may determine what to do subsequent, which instruments to make use of, and when to return the ultimate reply.
The subsequent evolutionary step is to create groups of such brokers that may collaborate with one another. This strategy is logical because it mirrors human interactions. We work in groups the place every member has a selected position:
The product supervisor proposes the following venture to work on.The designer creates its feel and look.The software program engineer develops the answer.The analyst examines the information to make sure it performs as anticipated and identifies methods to enhance the product for patrons.
Equally, we will create a workforce of AI brokers, every specializing in one area. They’ll collaborate and attain a ultimate conclusion collectively. Simply as specialization enhances efficiency in actual life, it might additionally profit the efficiency of AI brokers.
One other benefit of this strategy is elevated flexibility. Every agent can function with its personal immediate, set of instruments and even LLM. As an illustration, we will use totally different fashions for various elements of our system. You need to use GPT-4 for the agent that wants extra reasoning and GPT-3.5 for the one which does solely easy extraction. We will even fine-tune the mannequin for small particular duties and use it in our crew of brokers.
The potential drawbacks of this strategy are time and value. A number of interactions and data sharing between brokers require extra calls to LLM and devour further tokens. This might end in longer wait occasions and elevated bills.
There are a number of frameworks out there for multi-agent methods in the present day. Listed below are a number of the hottest ones:
AutoGen: Developed by Microsoft, AutoGen makes use of a conversational strategy and was one of many earliest frameworks for multi-agent methods,LangGraph: Whereas not strictly a multi-agent framework, LangGraph permits for outlining complicated interactions between actors utilizing a graph construction. So, it may also be tailored to create multi-agent methods.CrewAI: Positioned as a high-level framework, CrewAI facilitates the creation of “crews” consisting of role-playing brokers able to collaborating in varied methods.
I’ve determined to start out experimenting with multi-agent frameworks from CrewAI because it’s fairly extensively common and consumer pleasant. So, it seems like a great choice to start with.
On this article, I’ll stroll you thru the way to use CrewAI. As analysts, we’re the area specialists liable for documenting varied information sources and addressing associated questions. We’ll discover the way to automate these duties utilizing multi-agent frameworks.
Let’s begin with establishing the setting. First, we have to set up the CrewAI essential bundle and an extension to work with instruments.
pip set up crewaipip set up ‘crewai[tools]’
CrewAI was developed to work primarily with OpenAI API, however I might additionally prefer to strive it with an area mannequin. In accordance with the ChatBot Enviornment Leaderboard, the perfect mannequin you possibly can run in your laptop computer is Llama 3 (8b parameters). It will likely be probably the most possible choice for our use case.
We will entry Llama fashions utilizing Ollama. Set up is fairly easy. It’s good to obtain Ollama from the web site after which undergo the set up course of. That’s it.
Now, you possibly can take a look at the mannequin in CLI by operating the next command.
ollama run llama3
For instance, you possibly can ask one thing like this.
Let’s create a customized Ollama mannequin to make use of later in CrewAI.
We are going to begin with a ModelFile (documentation). I solely specified the bottom mannequin (llama3), temperature and cease sequence. Nonetheless, you would possibly add extra options. For instance, you possibly can decide the system message utilizing SYSTEM key phrase.
FROM llama3
# set parametersPARAMETER temperature 0.5PARAMETER cease End result
I’ve saved it right into a Llama3ModelFile file.
Let’s create a bash script to load the bottom mannequin for Ollama and create the customized mannequin we outlined in ModelFile.
#!/bin/zsh
# outline variablesmodel_name=”llama3″custom_model_name=”crewai-llama3″
# load the bottom modelollama pull $model_name
# create the mannequin fileollama create $custom_model_name -f ./Llama3ModelFile
Let’s execute this file.
chmod +x ./llama3_setup.sh./llama3_setup.sh
You could find each recordsdata on GitHub: Llama3ModelFile and llama3_setup.sh
We have to initialise the next environmental variables to make use of the native Llama mannequin with CrewAI.
os.environ[“OPENAI_API_BASE”]=’http://localhost:11434/v1′
os.environ[“OPENAI_MODEL_NAME”]=’crewai-llama3′ # custom_model_name from the bash script
os.environ[“OPENAI_API_KEY”] = “NA”
We’ve completed the setup and are able to proceed our journey.
As analysts, we frequently play the position of subject material specialists for information and a few data-related instruments. In my earlier workforce, we used to have a channel with nearly 1K contributors, the place we had been answering a number of questions on our information and the ClickHouse database we used as storage. It took us numerous time to handle this channel. It could be attention-grabbing to see whether or not such duties might be automated with LLMs.
For this instance, I’ll use the ClickHouse database. In case you’re , You may be taught extra about ClickHouse and the way to set it up domestically in my earlier article. Nonetheless, we gained’t utilise any ClickHouse-specific options, so be happy to stay to the database you realize.
I’ve created a reasonably easy information mannequin to work with. There are simply two tables in our DWH (Knowledge Warehouse): ecommerce_db.customers and ecommerce_db.classes. As you would possibly guess, the primary desk incorporates details about the customers of our service.
The ecommerce_db.classes desk shops details about consumer classes.
Concerning information supply administration, analysts usually deal with duties like writing and updating documentation and answering questions on this information. So, we’ll use LLM to jot down documentation for the desk within the database and train it to reply questions on information or ClickHouse.
However earlier than shifting on to the implementation, let’s be taught extra concerning the CrewAI framework and its core ideas.
The cornerstone of a multi-agent framework is an agent idea. In CrewAI, brokers are powered by role-playing. Function-playing is a tactic whenever you ask an agent to undertake a persona and behave like a top-notch backend engineer or useful buyer assist agent. So, when making a CrewAI agent, that you must specify every agent’s position, aim, and backstory in order that LLM is aware of sufficient to play this position.
The brokers’ capabilities are restricted with out instruments (capabilities that brokers can execute and get outcomes). With CrewAI, you should utilize one of many predefined instruments (for instance, to go looking the Web, parse an internet site, or do RAG on a doc), create a customized software your self or use LangChain instruments. So, it’s fairly straightforward to create a strong agent.
Let’s transfer on from brokers to the work they’re doing. Brokers are engaged on duties (particular assignments). For every process, we have to outline an outline, anticipated output (definition of accomplished), set of obtainable instruments and assigned agent. I actually like that these frameworks observe the managerial finest practices like a transparent definition of accomplished for the duties.
The subsequent query is the way to outline the execution order for duties: which one to work on first, which of them can run in parallel, and so on. CrewAI carried out processes to orchestrate the duties. It supplies a few choices:
Sequential —probably the most easy strategy when duties are referred to as one after one other.Hierarchical — when there’s a supervisor (specified as LLM mannequin) that creates and delegates duties to the brokers.
Additionally, CrewAI is engaged on a consensual course of. In such a course of, brokers will have the ability to make selections collaboratively with a democratic strategy.
There are different levers you should utilize to tweak the method of duties’ execution:
You may mark duties as “asynchronous”, then they are going to be executed in parallel, so it is possible for you to to get a solution quicker.You need to use the “human enter” flag on a process, after which the agent will ask for human approval earlier than finalising the output of this process. It might will let you add an oversight to the method.
We’ve outlined all the first constructing blocks and may talk about the holly grail of CrewAI — crew idea. The crew represents the workforce of brokers and the set of duties they are going to be engaged on. The strategy for collaboration (processes we mentioned above) may also be outlined on the crew degree.
Additionally, we will arrange the reminiscence for a crew. Reminiscence is essential for environment friendly collaboration between the brokers. CrewAI helps three ranges of reminiscence:
Quick-term reminiscence shops info associated to the present execution. It helps brokers to work collectively on the present process.Lengthy-term reminiscence is information concerning the earlier executions saved within the native database. The sort of reminiscence permits brokers to be taught from earlier iterations and enhance over time.Entity reminiscence captures and constructions details about entities (like personas, cities, and so on.)
Proper now, you possibly can solely swap on all forms of reminiscence for a crew with none additional customisation. Nonetheless, it doesn’t work with the Llama fashions.
We’ve discovered sufficient concerning the CrewAI framework, so it’s time to start out utilizing this information in apply.
Let’s begin with a easy process: placing collectively the documentation for our DWH. As we mentioned earlier than, there are two tables in our DWH, and I want to create an in depth description for them utilizing LLMs.
First strategy
To start with, we’d like to consider the workforce construction. Consider this as a typical managerial process. Who would you rent for such a job?
I might break this process into two elements: retrieving information from a database and writing documentation. So, we’d like a database specialist and a technical author. The database specialist wants entry to a database, whereas the author gained’t want any particular instruments.
Now, now we have a high-level plan. Let’s create the brokers.
For every agent, I’ve specified the position, aim and backstory. I’ve tried my finest to supply brokers with all of the wanted context.
database_specialist_agent = Agent(position = “Database specialist”,aim = “Present information to reply enterprise questions utilizing SQL”,backstory = ”’You’re an skilled in SQL, so you possibly can assist the workforce to assemble wanted information to energy their selections. You’re very correct and consider all of the nuances in information.”’,allow_delegation = False,verbose = True)
tech_writer_agent = Agent(position = “Technical author”,aim = ”’Write partaking and factually correct technical documentation for information sources or instruments”’,backstory = ”’ You’re an skilled in each expertise and communications, so you possibly can simply clarify even refined ideas.You base your work on the factual info supplied by your colleagues.Your texts are concise and might be simply understood by a large viewers. You employ skilled however reasonably a casual fashion in your communication.”’,allow_delegation = False,verbose = True)
We are going to use a easy sequential course of, so there’s no want for brokers to delegate duties to one another. That’s why I specified allow_delegation = False.
The subsequent step is setting the duties for brokers. However earlier than shifting to them, we have to create a customized software to hook up with the database.
First, I put collectively a perform to execute ClickHouse queries utilizing HTTP API.
CH_HOST = ‘http://localhost:8123’ # default deal with
def get_clickhouse_data(question, host = CH_HOST, connection_timeout = 1500):r = requests.put up(host, params = {‘question’: question}, timeout = connection_timeout)if r.status_code == 200:return r.textelse: return ‘Database returned the next error:n’ + r.textual content
When working with LLM brokers, it’s essential to make instruments fault-tolerant. For instance, if the database returns an error (status_code != 200), my code gained’t throw an exception. As an alternative, it’s going to return the error description to the LLM so it will probably try to resolve the difficulty.
To create a CrewAI customized software, we have to derive our class from crewai_tools.BaseTool, implement the _run technique after which create an occasion of this class.
from crewai_tools import BaseTool
class DatabaseQuery(BaseTool):identify: str = “Database Question”description: str = “Returns the results of SQL question execution”
def _run(self, sql_query: str) -> str:# Implementation goes herereturn get_clickhouse_data(sql_query)
database_query_tool = DatabaseQuery()
Now, we will set the duties for the brokers. Once more, offering clear directions and all of the context to LLM is essential.
table_description_task = Process(description = ”’Present the great overview for the information in desk {desk}, in order that it is simple to know the construction of the information. This process is essential to place collectively the documentation for our database”’,expected_output = ”’The great overview of {desk} within the md format. Embrace 2 sections: columns (checklist of columns with their sorts) and examples (the primary 30 rows from desk).”’,instruments = [database_query_tool],agent = database_specialist_agent)
table_documentation_task = Process(description = ”’Utilizing supplied details about the desk, put collectively the detailed documentation for this desk so that individuals can use it in apply”’,expected_output = ”’Nicely-written detailed documentation describing the information scheme for the desk {desk} in markdown format, that offers the desk overview in 1-2 sentences then then describes every columm. Construction the columns description as a markdown desk with column identify, sort and outline.”’,instruments = [],output_file=”table_documentation.md”,agent = tech_writer_agent)
You might need seen that I’ve used {desk} placeholder within the duties’ descriptions. We are going to use desk as an enter variable when executing the crew, and this worth shall be inserted into all placeholders.
Additionally, I’ve specified the output file for the desk documentation process to avoid wasting the ultimate outcome domestically.
Now we have all we’d like. Now, it’s time to create a crew and execute the method, specifying the desk we’re curious about. Let’s strive it with the customers desk.
crew = Crew(brokers = [database_specialist_agent, tech_writer_agent],duties = [table_description_task, table_documentation_task],verbose = 2)
outcome = crew.kickoff({‘desk’: ‘ecommerce_db.customers’})
It’s an thrilling second, and I’m actually wanting ahead to seeing the outcome. Don’t fear if execution takes a while. Brokers make a number of LLM calls, so it’s completely regular for it to take a couple of minutes. It took 2.5 minutes on my laptop computer.
We requested LLM to return the documentation in markdown format. We will use the next code to see the formatted end in Jupyter Pocket book.
from IPython.show import MarkdownMarkdown(outcome)
At first look, it seems nice. We’ve received the legitimate markdown file describing the customers’ desk.
However wait, it’s incorrect. Let’s see what information now we have in our desk.
The columns listed within the documentation are fully totally different from what now we have within the database. It’s a case of LLM hallucinations.
We’ve set verbose = 2 to get the detailed logs from CrewAI. Let’s learn by way of the execution logs to establish the foundation reason for the issue.
First, the database specialist couldn’t question the database as a consequence of issues with quotes.
The specialist didn’t handle to resolve this drawback. Lastly, this chain has been terminated by CrewAI with the next output: Agent stopped as a consequence of iteration restrict or time restrict.
This implies the technical author didn’t obtain any factual details about the information. Nonetheless, the agent continued and produced fully faux outcomes. That’s how we ended up with incorrect documentation.
Fixing the problems
Regardless that our first iteration wasn’t profitable, we’ve discovered quite a bit. Now we have (at the least) two areas for enchancment:
Our database software is simply too tough for the mannequin, and the agent struggles to make use of it. We will make the software extra tolerant by eradicating quotes from the start and finish of the queries. This answer will not be preferrred since legitimate SQL can finish with a quote, however let’s strive it.Our technical author isn’t basing its output on the enter from the database specialist. We have to tweak the immediate to focus on the significance of offering solely factual info.
So, let’s attempt to repair these issues. First, we’ll repair the software — we will leverage strip to get rid of quotes.
CH_HOST = ‘http://localhost:8123’ # default deal with
def get_clickhouse_data(question, host = CH_HOST, connection_timeout = 1500):r = requests.put up(host, params = {‘question’: question.strip(‘”‘).strip(“‘”)}, timeout = connection_timeout)if r.status_code == 200:return r.textelse: return ‘Database returned the next error:n’ + r.textual content
Then, it’s time to replace the immediate. I’ve included statements emphasizing the significance of sticking to the info in each the agent and process definitions.
tech_writer_agent = Agent(position = “Technical author”,aim = ”’Write partaking and factually correct technical documentation for information sources or instruments”’,backstory = ”’ You’re an skilled in each expertise and communications, so you possibly can simply clarify even refined ideas.Your texts are concise and might be simply understood by vast viewers. You employ skilled however reasonably casual fashion in your communication.You base your work on the factual info supplied by your colleagues. You follow the info within the documentation and use ONLY info supplied by the colleagues not including something.”’,allow_delegation = False,verbose = True)
table_documentation_task = Process(description = ”’Utilizing supplied details about the desk, put collectively the detailed documentation for this desk so that individuals can use it in apply”’,expected_output = ”’Nicely-written detailed documentation describing the information scheme for the desk {desk} in markdown format, that offers the desk overview in 1-2 sentences then then describes every columm. Construction the columns description as a markdown desk with column identify, sort and outline.The documentation is predicated ONLY on the data supplied by the database specialist with none additions.”’,instruments = [],output_file = “table_documentation.md”,agent = tech_writer_agent)
Let’s execute our crew as soon as once more and see the outcomes.
We’ve achieved a bit higher outcome. Our database specialist was capable of execute queries and examine the information, which is a big win for us. Moreover, we will see all of the related fields within the outcome desk, although there are many different fields as nicely. So, it’s nonetheless not totally right.
I as soon as once more seemed by way of the CrewAI execution log to determine what went incorrect. The difficulty lies in getting the checklist of columns. There’s no filter by database, so it returns some unrelated columns that seem within the outcome.
SELECT column_name FROM information_schema.columns WHERE table_name = ‘customers’
Additionally, after taking a look at a number of makes an attempt, I seen that the database specialist, every so often, executes choose * from <desk> question. It’d trigger some points in manufacturing as it’d generate a number of information and ship it to LLM.
Extra specialised instruments
We will present our agent with extra specialised instruments to enhance our answer. At the moment, the agent has a software to execute any SQL question, which is versatile and highly effective however susceptible to errors. We will create extra targeted instruments, comparable to getting desk construction and top-N rows from the desk. Hopefully, it’s going to cut back the variety of errors.
class TableStructure(BaseTool):identify: str = “Desk construction”description: str = “Returns the checklist of columns and their sorts”
def _run(self, desk: str) -> str:desk = desk.strip(‘”‘).strip(“‘”)return get_clickhouse_data(‘describe {desk} format TabSeparatedWithNames’.format(desk = desk))
class TableExamples(BaseTool):identify: str = “Desk examples”description: str = “Returns the primary N rows from the desk”
def _run(self, desk: str, n: int = 30) -> str:desk = desk.strip(‘”‘).strip(“‘”)return get_clickhouse_data(‘choose * from {desk} restrict {n} format TabSeparatedWithNames’.format(desk = desk, n = n))
table_structure_tool = TableStructure()table_examples_tool = TableExamples()
Now, we have to specify these instruments within the process and re-run our script. After the primary try, I received the next output from the Technical Author.
Process output: This ultimate reply supplies an in depth and factual description of the ecommerce_db.customers desk construction, together with column names, sorts, and descriptions. The documentation adheres to the supplied info from the database specialist with none additions or modifications.
Extra targeted instruments helped the database specialist retrieve the right desk info. Nonetheless, although the author had all the mandatory info, we didn’t get the anticipated outcome.
As we all know, LLMs are probabilistic, so I gave it one other strive. And hooray, this time, the outcome was fairly good.
It’s not good because it nonetheless consists of some irrelevant feedback and lacks the general description of the desk. Nonetheless, offering extra specialised instruments has undoubtedly paid off. It additionally helped to stop points when the agent tried to load all the information from the desk.
High quality assurance specialist
We’ve achieved fairly good outcomes, however let’s see if we will enhance them additional. A typical apply in multi-agent setups is high quality assurance, which provides the ultimate assessment stage earlier than finalising the outcomes.
Let’s create a brand new agent — a High quality Assurance Specialist, who shall be in control of assessment.
qa_specialist_agent = Agent(position = “High quality Assurance specialist”,aim = “””Guarantee the very best high quality of the documentation we offer (that it is right and simple to know)”””,backstory = ”’You’re employed as a High quality Assurance specialist, checking the work from the technical author and guaranteeing that it is inline with our highest requirements.It’s good to verify that the technical author supplies the total full solutions and make no assumptions. Additionally, that you must make it possible for the documentation addresses all of the questions and is straightforward to know.”’,allow_delegation = False,verbose = True)
Now, it’s time to explain the assessment process. I’ve used the context parameter to specify that this process requires outputs from each table_description_task and table_documentation_task.
qa_review_task = Process(description = ”’Evaluate the draft documentation supplied by the technical author.Be sure that the documentation totally solutions all of the questions: the aim of the desk and its construction within the type of desk. Guarantee that the documentation is according to the data supplied by the database specialist. Double verify that there aren’t any irrelevant feedback within the ultimate model of documentation.”’,expected_output = ”’The ultimate model of the documentation in markdown format that may be printed. The documentation ought to totally deal with all of the questions, be constant and observe our skilled however casual tone of voice.”’,instruments = [],context = [table_description_task, table_documentation_task],output_file=”checked_table_documentation.md”,agent = qa_specialist_agent)
Let’s replace our crew and run it.
full_crew = Crew(brokers=[database_specialist_agent, tech_writer_agent, qa_specialist_agent],duties=[table_description_task, table_documentation_task, qa_review_task],verbose = 2,reminiscence = False # do not work with Llama)
full_result = full_crew.kickoff({‘desk’: ‘ecommerce_db.customers’})
We now have extra structured and detailed documentation because of the addition of the QA stage.
Delegation
With the addition of the QA specialist, it could be attention-grabbing to check the delegation mechanism. The QA specialist agent might need questions or requests that it might delegate to different brokers.
I attempted utilizing the delegation with Llama 3, however it didn’t go nicely. Llama 3 struggled to name the co-worker software appropriately. It couldn’t specify the right co-worker’s identify.
We achieved fairly good outcomes with an area mannequin that may run on any laptop computer, however now it’s time to change gears and use a far more highly effective mannequin — GPT-4o.
To do it, we simply must replace the next setting variables.
os.environ[“OPENAI_MODEL_NAME”] = ‘gpt-4o’ os.environ[“OPENAI_API_KEY”] = config[‘OPENAI_API_KEY’] # your OpenAI key
To modify on the delegation, we should always specify allow_delegation = True for the QA specialist agent.
Additionally, we will use helpful reminiscence performance for OpenAI fashions, as talked about above. The reminiscence will enable our brokers to share their data with one another throughout execution and leverage long-term reminiscence to get info from earlier executions.
full_crew = Crew(brokers = [database_specialist_agent, tech_writer_agent, qa_specialist_agent],duties = [table_description_task, table_documentation_task, qa_review_task],verbose = 2,reminiscence = True )
full_result = full_crew.kickoff({‘desk’: ‘ecommerce_db.customers’})
Let’s see the CrewAI execution logs to know how delegation works. Listed below are all of the logs for the QA specialist. We will see that it reached out to the database specialist to double-check the data.
Thought: I must assessment the supplied draft documentation to make sure it totally solutions all of the questions and is full, right, and simple to know. Particularly, I would like to make sure that it explains the aim of the desk, its construction, and consists of related examples with none irrelevant feedback.
First, I’ll evaluate the 2 drafts to establish any discrepancies and lacking info. Then, I’ll confirm the accuracy and completeness of the data supplied.
**Comparability:**1. **Introduction:**- First draft: Contains an introduction and examples.- Second draft: Provides a extra detailed introduction concerning the goal and significance of the desk.
2. **Columns:**- Each drafts have the identical column construction and descriptions.
3. **Further Data:**- Each drafts embody comparable further info, however the second draft is extra concise.
4. **Examples:**- The primary draft consists of examples, that are lacking within the second draft.
5. **Ultimate Checks:**- Guarantee there aren’t any irrelevant feedback.- Confirm consistency with info supplied by the database specialist.
Motion: Ask query to co-workerAction Enter:
<– omitted logs from the database specialist –>
Primarily based on the supplied context and examples for the `ecommerce_db.customers` desk, the column descriptions and examples seem correct. Listed below are the small print:- `user_id`: This column incorporates a novel identifier for every consumer. The supplied examples (e.g., 1000001, 1000002) align with this description as they’re distinctive numeric identifiers.
– `nation`: This column specifies the nation of the consumer. The supplied examples (e.g., United Kingdom, France, Germany, Netherlands) are all legitimate nation names.
– `is_active`: This column signifies whether or not the consumer is energetic (1) or not (0). The supplied examples (e.g., 0, 1) appropriately characterize this binary standing.
– `age`: This column exhibits the age of the consumer. The supplied examples (e.g., 70, 87, 88, 25, 48, 78, 65, 31, 66, 73) are all legitimate ages.
Subsequently, the column descriptions and examples supplied for the `ecommerce_db.customers` desk are correct and meet the anticipated standards.
Thought: Primarily based on the commentary from the database specialist, the column descriptions and examples supplied for the `ecommerce_db.customers` desk are correct. Now, I’ll consolidate the perfect components from each drafts,guaranteeing the documentation is full, clear, and freed from irrelevant feedback.
Motion: Finalize the documentation in markdown format, incorporating the detailed introduction, examples, and guaranteeing the tone is skilled however casual.
After I tried the delegation for the primary time, I didn’t allow reminiscence, which led to incorrect outcomes. The information specialist and the technical author initially returned the right info. Nonetheless, when the QA specialist returned with the follow-up questions, they began to hallucinate. So, it seems like delegation works higher when reminiscence is enabled.
Right here’s the ultimate output from GPT-4o. The outcome seems fairly good now. We undoubtedly can use LLMs to automate documentation.
So, the primary process has been solved!
I used the identical script to generate documentation for the ecommerce_db.classes desk as nicely. It will likely be helpful for our subsequent process. So, let’s not waste any time and transfer on.
Our subsequent process is answering questions primarily based on the documentation because it’s frequent for a lot of information analysts (and different specialists).
We are going to begin easy and can create simply two brokers:
The documentation assist specialist shall be answering questions primarily based on the docs,The assist QA agent will assessment the reply earlier than sharing it with the client.
We might want to empower the documentation specialist with a few instruments that may enable them to see all of the recordsdata saved within the listing and browse the recordsdata. It’s fairly easy since CrewAI has carried out such instruments.
from crewai_tools import DirectoryReadTool, FileReadTool
documentation_directory_tool = DirectoryReadTool(listing = ‘~/crewai_project/ecommerce_documentation’)
base_file_read_tool = FileReadTool()
Nonetheless, since Llama 3 retains battling quotes when calling instruments, I needed to create a customized software on high of the FileReaderTool to beat this challenge.
from crewai_tools import BaseTool
class FileReadToolUPD(BaseTool):identify: str = “Learn a file’s content material”description: str = “A software that can be utilized to learn a file’s content material.”
def _run(self, file_path: str) -> str:# Implementation goes herereturn base_file_read_tool._run(file_path = file_path.strip(‘”‘).strip(“‘”))
file_read_tool = FileReadToolUPD()
Subsequent, as we did earlier than, we have to create brokers, duties and crew.
data_support_agent = Agent(position = “Senior Knowledge Assist Agent”,aim = “Be probably the most useful assist for you colleagues”,backstory = ”’You’re employed as a assist for data-related questions within the firm. Regardless that you are a giant skilled in our information warehouse, you double verify all of the info in documentation. Our documentation is totally up-to-date, so you possibly can totally depend on it when answering questions (you needn’t verify the precise information in database).Your work is essential for the workforce success. Nonetheless, keep in mind that examples of desk rows do not present all of the doable values. It’s good to make sure that you present the absolute best assist: answering all of the questions, making no assumptions and sharing solely the factual information.Be inventive strive your finest to resolve the client drawback. ”’,allow_delegation = False,verbose = True)
qa_support_agent = Agent(position = “Assist High quality Assurance Agent”,aim = “””Guarantee the very best high quality of the solutions we offer to the shoppers”””,backstory = ”’You’re employed as a High quality Assurance specialist, checking the work from assist brokers and guaranteeing that it is inline with our highest requirements.It’s good to verify that the agent supplies the total full solutions and make no assumptions. Additionally, that you must make it possible for the documentation addresses all of the questions and is straightforward to know.”’,allow_delegation = False,verbose = True)
draft_data_answer = Process(description = ”’Crucial buyer {buyer} reached out to you with the next query:“`{query}“`
Your process is to supply the perfect reply to all of the factors within the query utilizing all out there info and never making any assumprions. If you do not have sufficient info to reply the query, simply say that you do not know.”’,expected_output = ”’The detailed informative reply to the client’s query that addresses all the purpose talked about. Guarantee that reply is full and stict to info (with none further info not primarily based on the factual information)”’,instruments = [documentation_directory_tool, file_read_tool], agent = data_support_agent)
answer_review = Process(description = ”’Evaluate the draft reply supplied by the assist agent.Be sure that the it totally solutions all of the questions talked about within the preliminary inquiry. Guarantee that the reply is constant and does not embody any assumptions.”’,expected_output = ”’The ultimate model of the reply in markdown format that may be shared with the client. The reply ought to totally deal with all of the questions, be constant and observe our skilled however casual tone of voice. We’re very chill and pleasant firm, so remember to incorporate all of the well mannered phrases.”’,instruments = [], agent = qa_support_agent)
qna_crew = Crew(brokers = [data_support_agent, qa_support_agent],duties = [draft_data_answer, answer_review],verbose = 2,reminiscence = False # do not work with Llama)
Let’s see the way it works in apply.
outcome = qna_crew.kickoff({‘buyer’: “Max”, ‘query’: “””Hey workforce, I hope you are doing nicely. I would like to seek out the numbers earlier than our CEO presentation tomorrow, so I’ll actually admire your assist.I must calculate the variety of classes from our Home windows customers in 2023. I’ve tried to seek out the desk with such information in our information warehouse, however wasn’t capable of. Do you’ve gotten any concepts whether or not we retailer the wanted information someplace, in order that I can question it? “””})
We’ve received a well mannered, sensible and useful reply in return. That’s actually nice.
**Whats up Max,**
Thanks for reaching out along with your query! I am glad that can assist you discover the variety of classes from Home windows customers in 2023. After reviewing our documentation, I discovered that we do retailer information associated to classes and customers in our ecommerce database, particularly within the `ecommerce_db.classes` desk.
To reply your query, I can give you a step-by-step information on the way to question this desk utilizing SQL. First, you should utilize the `session_id` column together with the `os` column filtering for “Home windows” and the `action_date` column filtering for dates in 2023. Then, you possibly can group the outcomes by `os` utilizing the `GROUP BY` clause to rely the variety of classes that meet these situations.
This is a pattern SQL question that ought to provide the desired output:
“`sqlSELECT COUNT(*) FROM ecommerce_db.classes WHERE os = ‘Home windows’ AND action_date BETWEEN ‘2023-01-01’ AND ‘2023-12-31’GROUP BY os;“`
This question will return the entire variety of classes from Home windows customers in 2023. I hope this helps! In case you have any additional questions or want extra help, please do not hesitate to ask.
Let’s complicate the duty a bit. Suppose we will get not solely questions on our information but in addition about our software (ClickHouse). So, we could have one other agent within the crew — ClickHouse Guru. To provide our CH agent some data, I’ll share a documentation web site with it.
from crewai_tools import ScrapeWebsiteTool, WebsiteSearchToolch_documenation_tool = ScrapeWebsiteTool(‘https://clickhouse.com/docs/en/guides/creating-tables’)
If that you must work with a prolonged doc, you would possibly strive utilizing RAG (Retrieval Augmented era) — WebsiteSearchTool. It’s going to calculate embeddings and retailer them domestically in ChromaDB. In our case, we’ll follow a easy web site scraper software.
Now that now we have two subject material specialists, we have to determine who shall be engaged on the questions. So, it’s time to make use of a hierarchical course of and add a supervisor to orchestrate all of the duties.
CrewAI supplies the supervisor implementation, so we solely must specify the LLM mannequin. I’ve picked the GPT-4o.
from langchain_openai import ChatOpenAIfrom crewai import Course of
complext_qna_crew = Crew(brokers = [ch_support_agent, data_support_agent, qa_support_agent],duties = [draft_ch_answer, draft_data_answer, answer_review],verbose = 2,manager_llm = ChatOpenAI(mannequin=’gpt-4o’, temperature=0), course of = Course of.hierarchical, reminiscence = False )
At this level, I needed to swap from Llama 3 to OpenAI fashions once more to run a hierarchical course of because it hasn’t labored for me with Llama (just like this challenge).
Now, we will strive our new crew with several types of questions (both associated to our information or ClickHouse database).
ch_result = complext_qna_crew.kickoff({‘buyer’: “Maria”, ‘query’: “””Good morning, workforce. I am utilizing ClickHouse to calculate the variety of clients. Might you please remind whether or not there’s an choice so as to add totals in ClickHouse?”””})
doc_result = complext_qna_crew.kickoff({‘buyer’: “Max”, ‘query’: “””Hey workforce, I hope you are doing nicely. I would like to seek out the numbers earlier than our CEO presentation tomorrow, so I’ll actually admire your assist.I must calculate the variety of classes from our Home windows customers in 2023. I’ve tried to seek out the desk with such information in our information warehouse, however wasn’t capable of. Do you’ve gotten any concepts whether or not we retailer the wanted information someplace, in order that I can question it. “””})
If we have a look at the ultimate solutions and logs (I’ve omitted them right here since they’re fairly prolonged, however yow will discover them and full logs on GitHub), we’ll see that the supervisor was capable of orchestrate appropriately and delegate duties to co-workers with related data to handle the client’s query. For the primary (ClickHouse-related) query, we received an in depth reply with examples and doable implications of utilizing WITH TOTALS performance. For the data-related query, fashions returned roughly the identical info as we’ve seen above.
So, we’ve constructed a crew that may reply varied forms of questions primarily based on the documentation, whether or not from an area file or an internet site. I believe it’s a wonderful outcome.
You could find all of the code on GitHub.
On this article, we’ve explored utilizing the CrewAI multi-agent framework to create an answer for writing documentation primarily based on tables and answering associated questions.
Given the in depth performance we’ve utilised, it’s time to summarise the strengths and weaknesses of this framework.
Total, I discover CrewAI to be an extremely helpful framework for multi-agent methods:
It’s easy, and you’ll construct your first prototype rapidly.Its flexibility permits to resolve fairly refined enterprise issues.It encourages good practices like role-playing.It supplies many helpful instruments out of the field, comparable to RAG and an internet site parser.The assist of several types of reminiscence enhances the brokers’ collaboration.Constructed-in guardrails assist forestall brokers from getting caught in repetitive loops.
Nonetheless, there are areas that could possibly be improved:
Whereas the framework is easy and simple to make use of, it’s not very customisable. As an illustration, you presently can’t create your individual LLM supervisor to orchestrate the processes.Generally, it’s fairly difficult to get the total detailed info from the documentation. For instance, it’s clear that CrewAI carried out some guardrails to stop repetitive perform calls, however the documentation doesn’t totally clarify the way it works.One other enchancment space is transparency. I like to know how frameworks work beneath the hood. For instance, in Langchain, you should utilize langchain.debug = True to see all of the LLM calls. Nonetheless, I haven’t discovered the way to get the identical degree of element with CrewAI.The total assist for the native fashions can be an excellent addition, as the present implementation both lacks some options or is tough to get working correctly.
The area and instruments for LLMs are evolving quickly, so I’m hopeful that we’ll see a number of progress within the close to future.
Thank you a large number for studying this text. I hope this text was insightful for you. In case you have any follow-up questions or feedback, please depart them within the feedback part.
This text is impressed by the “Multi AI Agent Programs with CrewAI” brief course from DeepLearning.AI.