From RAG to material: Classes discovered from constructing real-world RAGs at GenAIIC – Half 1

The AWS Generative AI Innovation Heart (GenAIIC) is a staff of AWS science and technique consultants who’ve deep data of generative AI. They assist AWS prospects jumpstart their generative AI journey by constructing proofs of idea that use generative AI to carry enterprise worth. Because the inception of AWS GenAIIC in Might 2023, we now have witnessed excessive buyer demand for chatbots that may extract data and generate insights from huge and infrequently heterogeneous data bases. Such use circumstances, which increase a big language mannequin’s (LLM) data with exterior information sources, are often called Retrieval-Augmented Era (RAG).

This two-part sequence shares the insights gained by AWS GenAIIC from direct expertise constructing RAG options throughout a variety of industries. You should utilize this as a sensible information to constructing higher RAG options.

On this first submit, we give attention to the fundamentals of RAG structure and the right way to optimize text-only RAG. The second submit outlines the right way to work with a number of information codecs similar to structured information (tables, databases) and pictures.

Anatomy of RAG

RAG is an environment friendly option to present an FM with further data by utilizing exterior information sources and is depicted within the following diagram:

• Retrieval: Based mostly on a person’s query (1), related data is retrieved from a data base (2) (for instance, an OpenSearch index).
• Augmentation: The retrieved data is added to the FM immediate (3.a) to enhance its data, together with the person question (3.b).
• Era: The FM generates a solution (4) by utilizing the knowledge supplied within the immediate.

The next is a normal diagram of a RAG workflow. From left to proper are the retrieval, the augmentation, and the era. In apply, the data base is usually a vector retailer.

A deeper dive within the retriever

In a RAG structure, the FM will base its reply on the knowledge supplied by the retriever. Subsequently, a RAG is just nearly as good as its retriever, and lots of the ideas that we share in our sensible information are about the right way to optimize the retriever. However what’s a retriever precisely? Broadly talking, a retriever is a module that takes a question as enter and outputs related paperwork from a number of data sources related to that question.

Doc ingestion

In a RAG structure, paperwork are sometimes saved in a vector retailer. As proven within the following diagram, vector shops are populated by chunking the paperwork into manageable items (1) (if a doc is brief sufficient, chunking may not be required) and remodeling every chunk of the doc right into a high-dimensional vector utilizing a vector embedding (2), such because the Amazon Titan embeddings mannequin. These embeddings have the attribute that two chunks of texts which can be semantically shut have vector representations which can be additionally shut in that embedding (within the sense of the cosine or Euclidean distance).

The next diagram illustrates the ingestion of textual content paperwork within the vector retailer utilizing an embedding mannequin. Notice that the vectors are saved alongside the corresponding textual content chunk (3), in order that at retrieval time, while you determine the chunks closest to the question, you’ll be able to return the textual content chunk to be handed to the FM immediate.

Semantic search

Vector shops permit for environment friendly semantic search: as proven within the following diagram, given a person question (1), we vectorize it (2) (utilizing the identical embedding because the one which was used to construct the vector retailer) after which search for the closest vectors within the vector retailer (3), which can correspond to the doc chunks which can be semantically closest to the preliminary question (4). Though vector shops and semantic search have grow to be the default in RAG architectures, extra conventional keyword-based search remains to be helpful, particularly when trying to find domain-specific phrases (similar to technical jargon) or names. Hybrid search is a manner to make use of each semantic search and key phrases to rank a doc, and we’ll give extra particulars on this system within the part on superior RAG strategies.

The next diagram illustrates the retrieval of textual content paperwork which can be semantically near the person question. You need to use the identical embedding mannequin at ingestion time and at search time.

Implementation on AWS

A RAG chatbot might be arrange in a matter of minutes utilizing Amazon Bedrock Data Bases. The data base might be linked to an Amazon Easy Storage Service (Amazon S3) bucket and can routinely chunk and index the paperwork it comprises in an OpenSearch index, which can act because the vector retailer. The retrieve_and_generate API does each the retrieval and a name to an FM (Amazon Titan or Anthropic’s Claude household of fashions on Amazon Bedrock), for a completely managed answer. The retrieve API solely implements the retrieval part and permits for a extra customized method downstream, similar to doc submit processing earlier than calling the FM individually.

On this weblog submit, we’ll present ideas and code to optimize a completely customized RAG answer with the next elements:

• An OpenSearch Serverless vector search assortment because the vector retailer
• Customized chunking and ingestion capabilities to ingest the paperwork within the OpenSearch index
• A customized retrieval perform that takes a person question as an enter and outputs the related paperwork from the OpenSearch index
• FM calls to your mannequin of alternative on Amazon Bedrock to generate the ultimate reply.

On this submit, we give attention to a customized answer to assist readers perceive the internal workings of RAG. Many of the ideas we offer might be tailored to work with Amazon Bedrock Data Bases, and we’ll level this out within the related sections.

Overview of RAG use circumstances

Whereas working with prospects on their generative AI journey, we encountered a wide range of use circumstances that match throughout the RAG paradigm. In conventional RAG use circumstances, the chatbot depends on a database of textual content paperwork (.doc, .pdf, or .txt). Partly 2 of this submit, we’ll focus on the right way to prolong this functionality to pictures and structured information. For now, we’ll give attention to a typical RAG workflow: the enter is a person query, and the output is the reply to that query, derived from the related textual content chunks or paperwork retrieved from the database. Use circumstances embody the next:

• Customer support– This may embody the next:
  • Inner– Stay brokers use an inside chatbot to assist them reply buyer questions.
  • Exterior– Clients instantly chat with a generative AI chatbot.
  • Hybrid– The mannequin generates sensible replies for stay brokers that they will edit earlier than sending to prospects.
• Worker coaching and assets– On this use case, chatbots can use worker coaching manuals, HR assets, and IT service paperwork to assist staff onboard quicker or discover the knowledge they should troubleshoot inside points.
• Industrial upkeep– Upkeep manuals for advanced machines can have a number of hundred pages. Constructing a RAG answer round these manuals helps upkeep technicians discover related data quicker. Notice that upkeep manuals usually have photos and schemas, which might put them in a multimodal bucket.
• Product data search– Area specialists must determine related merchandise for a given use case, or conversely discover the proper technical details about a given product.
• Retrieving and summarizing monetary information– Analysts want essentially the most up-to-date data on markets and the economic system and depend on giant databases of stories or commentary articles. A RAG answer is a option to effectively retrieve and summarize the related data on a given matter.

Within the following sections, we’ll give ideas that you should utilize to optimize every facet of the RAG pipeline (ingestion, retrieval, and reply era) relying on the underlying use case and information format. To confirm that the modifications enhance the answer, you first want to have the ability to assess the efficiency of the RAG answer.

Evaluating a RAG answer

Opposite to conventional machine studying (ML) fashions, for which analysis metrics are nicely outlined and simple to compute, evaluating a RAG framework remains to be an open downside. First, gathering floor fact (data identified to be right) for the retrieval part and the era part is time consuming and requires human intervention. Secondly, even with a number of question-and-answer pairs out there, it’s troublesome to routinely consider if the RAG reply is shut sufficient to the human reply.

In our expertise, when a RAG system performs poorly, we discovered the retrieval half to virtually all the time be the perpetrator. Giant pre-trained fashions similar to Anthropic’s Claude mannequin will generate high-quality solutions if supplied with the proper data, and we discover two predominant failure modes:

• The related data isn’t current within the retrieved paperwork: On this case, the FM can attempt to make up a solution or use its personal data to reply. Including guardrails in opposition to such conduct is important.
• Related data is buried inside an extreme quantity of irrelevant information: When the scope of the retriever is simply too broad, the FM can get confused and begin mixing up a number of information sources, leading to a mistaken reply. Extra superior fashions similar to Anthropic’s Claude Sonnet 3.5 and Opus are reported to be extra sturdy in opposition to such conduct, however that is nonetheless a threat to concentrate on.

To judge the standard of the retriever, you should utilize the next conventional retrieval metrics:

• High-k accuracy: Measures whether or not at the very least one related doc is discovered throughout the high ok retrieved paperwork.
• Imply Reciprocal Rank (MRR)– This metric considers the rating of the retrieved paperwork. It’s calculated as the typical of the reciprocal ranks (RR) for every question. The RR is the inverse of the rank place of the primary related doc. For instance, if the primary related doc is in third place, the RR is 1/3. A better MRR signifies that the retriever can rank essentially the most related paperwork increased.
• Recall– This metric measures the power of the retriever to retrieve related paperwork from the corpus. It’s calculated because the variety of related paperwork which can be efficiently retrieved over the whole variety of related paperwork. Increased recall signifies that the retriever can discover a lot of the related data.
• Precision– This metric measures the power of the retriever to retrieve solely related paperwork and keep away from irrelevant ones. It’s calculated by the variety of related paperwork efficiently retrieved over the whole variety of paperwork retrieved. Increased precision signifies that the retriever isn’t retrieving too many irrelevant paperwork.

Notice that if the paperwork are chunked, the metrics should be computed on the chunk stage. This implies the bottom fact to judge a retriever is pairs of query and record of related doc chunks. In lots of circumstances, there is just one chunk that comprises the reply to the query, so the bottom fact turns into query and related doc chunk.

To judge the standard of the generated response, two predominant choices are:

• Analysis by subject material consultants: this gives the best reliability by way of analysis however can’t scale to numerous questions and slows down iterations on the RAG answer.
• Analysis by FM (additionally known as LLM-as-a-judge):
  • With a human-created start line: Present the FM with a set of floor fact question-and-answer pairs and ask the FM to judge the standard of the generated reply by evaluating it to the bottom fact one.
  • With an FM-generated floor fact: Use an FM to generate question-and-answer pairs for given chunks, after which use this as a floor fact, earlier than resorting to an FM to match RAG solutions to that floor fact.

We suggest that you just use an FM for evaluations to iterate quicker on enhancing the RAG answer, however to make use of subject-matter consultants (or at the very least human analysis) to offer a closing evaluation of the generated solutions earlier than deploying the answer.

A rising variety of libraries provide automated analysis frameworks that depend on further FMs to create a floor fact and consider the relevance of the retrieved paperwork in addition to the standard of the response:

• Ragas– This framework provides FM-based metrics beforehand described, similar to context recall, context precision, reply faithfulness, and reply relevancy. It must be tailored to Anthropic’s Claude fashions due to its heavy dependence on particular prompts.
• LlamaIndex– This framework gives a number of modules to independently consider the retrieval and era elements of a RAG system. It additionally integrates with different instruments similar to Ragas and DeepEval. It comprises modules to create floor fact (query-and-context pairs and question-and-answer pairs) utilizing an FM, which alleviates the usage of time-consuming human assortment of floor fact.
• RefChecker– That is an Amazon Science library centered on fine-grained hallucination detection.

Troubleshooting RAG

Analysis metrics give an total image of the efficiency of retrieval and era, however they don’t assist diagnose points. Diving deeper into poor responses might help you perceive what’s inflicting them and what you are able to do to alleviate the problem. You may diagnose the problem by taking a look at analysis metrics and in addition by having a human evaluator take a better have a look at each the LLM reply and the retrieved paperwork.

The next is a quick overview of points and potential fixes. We’ll describe every of the strategies in additional element, together with real-world use circumstances and code examples, within the subsequent part.

• The related chunk wasn’t retrieved (retriever has low high ok accuracy and low recall or noticed by human analysis):
  • Strive rising the variety of paperwork retrieved by the closest neighbor search and re-ranking the outcomes to chop again on the variety of chunks after retrieval.
  • Strive hybrid search. Utilizing key phrases together with semantic search (often called hybrid search) may assist, particularly if the queries include names or domain-specific jargon.
  • Strive question rewriting. Having an FM detect the intent or rewrite the question might help create a question that’s higher suited to the retriever. As an example, a person question similar to “What data do you have got within the data base in regards to the financial outlook in China?” comprises a variety of context that isn’t related to the search and can be extra environment friendly if rewritten as “financial outlook in China” for search functions.

• Too many chunks had been retrieved (retriever has low precision or noticed by human analysis):
  • Strive utilizing key phrase matching to limit the search outcomes. For instance, when you’re on the lookout for details about a selected entity or property in your data base, solely retrieve paperwork that explicitly point out them.
  • Strive metadata filtering in your OpenSearch index. For instance, when you’re on the lookout for data in information articles, attempt utilizing the date subject to filter solely the newest outcomes.
  • Strive utilizing question rewriting to get the proper metadata filtering. This superior method makes use of the FM to rewrite the person question as a extra structured question, permitting you to take advantage of OpenSearch filters. For instance, when you’re on the lookout for the specs of a selected product in your database, the FM can extract the product identify from the question, and you may then use the product identify subject to filter out the product identify.
  • Strive utilizing reranking to chop down on the variety of chunks handed to the FM.
• A related chunk was retrieved, nevertheless it’s lacking some context (can solely be assessed by human analysis):
  • Strive altering the chunking technique. Understand that small chunks are good for exact questions, whereas giant chunks are higher for questions that require a broad context:
    • Strive rising the chunk dimension and overlap as a primary step.
    • Strive utilizing section-based chunking. In case you have structured paperwork, use sections delimiters to chop your paperwork into chunks to have extra coherent chunks. Bear in mind that you just may lose among the extra fine-grained context in case your chunks are bigger.
  • Strive small-to-large retrievers. If you wish to preserve the fine-grained particulars of small chunks however be sure to retrieve all of the related context, small-to-large retrievers will retrieve your chunk together with the earlier and subsequent ones.
• If not one of the above assist:
  • Think about coaching a customized embedding.
• The retriever isn’t at fault, the issue is with FM era (evaluated by a human or LLM):
  • Strive immediate engineering to mitigate hallucinations.
  • Strive prompting the FM to make use of quotes in its solutions, to permit for handbook truth checking.
  • Strive utilizing one other FM to judge or right the reply.

A sensible information to enhancing the retriever

Notice that not all of the strategies that comply with must be applied collectively to optimize your retriever—some may even have reverse results. Use the previous troubleshooting information to get a shortlist of what may work, then have a look at the examples within the corresponding sections that comply with to evaluate if the tactic might be helpful to your retriever.

Hybrid search

Instance use case: A big producer constructed a RAG chatbot to retrieve product specs. These paperwork include technical phrases and product names. Think about the next instance queries:

query_1 = "What's the viscosity of product XYZ?"
query_2 = "How viscous is XYZ?"

The queries are equal and must be answered with the identical doc. The key phrase part will just remember to’re boosting paperwork mentioning the identify of the product, XYZ whereas the semantic part will be sure that paperwork containing viscosity get a excessive rating, even when the question comprises the phrase viscous.

Combining vector search with key phrase search can successfully deal with domain-specific phrases, abbreviations, and product names that embedding fashions may wrestle with. Virtually, this may be achieved in OpenSearch by combining a k-nearest neighbors (k-NN) question with key phrase matching. The weights for the semantic search in comparison with key phrase search might be adjusted. See the next instance code:

vector_embedding = compute_embedding(question)
dimension = 10
semantic_weight = 10
keyword_weight = 1
search_query = {"dimension":dimension, "question": { "bool": { "ought to":[] , "should":[] } } }
    # semantic search
    search_query['query']['bool']['should'].append(
            {"function_score": 
             { "question": 
              {"knn": 
               {"vector_field": 
                {"vector": vector_embedding, 
                "ok": 10 # The variety of nearest neighbors to retrieve
                }}}, 
              "weight": semantic_weight } })
              
    # key phrase search
    search_query['query']['bool']['should'].append({
             "function_score": 
            { "question": 
             {"match": 
             # This can improve the rating of chunks that match the phrases within the question
              {"chunk_text":  question} 
              },
             "weight": keyword_weight } })

Amazon Bedrock Data Bases additionally helps hybrid search, however you’ll be able to’t alter the weights for semantic in comparison with key phrase search.

Including metadata data to textual content chunks

Instance use case: Utilizing the identical instance of a RAG chatbot for product specs, take into account product specs which can be a number of pages lengthy and the place the product identify is just current within the header of the doc. When ingesting the doc into the data base, it’s chunked into smaller items for the embedding mannequin, and the product identify solely seems within the first chunk, which comprises the header. See the next instance:

# Notice: the next doc was generated by Anthropic’s Claude Sonnet 
# and doesn't include details about an actual product

document_name = "Chemical Properties for Product XYZ"

chunk_1 = """
Product Description:
XYZ is a multi-purpose cleansing answer designed for industrial and business use. 
It's a concentrated liquid formulation containing anionic and non-ionic surfactants, 
solvents, and alkaline builders.

Chemical Composition:
- Water (CAS No. 7732-18-5): 60-80%
- 2-Butoxyethanol (CAS No. 111-76-2): 5-10%
- Sodium Hydroxide (CAS No. 1310-73-2): 2-5%
- Ethoxylated Alcohols (CAS No. 68439-46-3): 1-3%
- Sodium Metasilicate (CAS No. 6834-92-0): 1-3%
- Perfume (Proprietary Combination): <1%
"""

# chunk 2 under does not include any point out of "XYZ"
chunk_2 = """
Bodily Properties:
- Look: Clear, yellow liquid
- Odor: Gentle, citrus perfume
- pH (focus): 12.5 - 13.5
- Particular Gravity: 1.05 - 1.10
- Solubility in Water: Full
- VOC Content material: <10%

Shelf-life:
When saved in its authentic, unopened container at temperatures between 15°C and 25°C,
 the product has a shelf lifetime of 24 months from the date of manufacture.
As soon as opened, the shelf life is decreased as a consequence of potential contamination and publicity to
 air. It is suggested to make use of the product inside 6 months after opening the container.
"""

# append the doc identify to the chunks to enhance context,
# now chunk 2 will include the product identify

chunk_1 = document_name + chunk_1
chunk_2 = document_name + chunk_2

document_title = "Resolving community points"

chunk_1 = """
[....]

# Troubleshooting web entry:

1. Examine your bodily connections:
   - Be certain that the Ethernet cable (if utilizing a wired connection) is securely 
   plugged into each your laptop and the modem/router.
   - If utilizing a wi-fi connection, test that your machine's Wi-Fi is turned 
   on and linked to the proper community.

2. Restart your units:
   - Reboot your laptop, laptop computer, or cell machine.
   - Energy cycle your modem and router by unplugging them from the facility supply, 
   ready for a minute, after which plugging them again in.

"""

chunk_2 = """
3. Examine for community outages:
   - Contact your web service supplier (ISP) to inquire about any identified 
   outages or service disruptions in your space.
   - Go to your ISP's web site or test their social media channels for updates on 
   service standing.
  
4. Examine for interference:
   - If utilizing a wi-fi connection, attempt shifting your machine nearer to the router or entry level.
   - Determine and eradicate potential sources of interference, similar to microwaves, cordless telephones, or different wi-fi units working on the identical frequency.

# Router configuration

[....]
"""

document_name = doc['document_name'] 
current_chunk = doc['current_chunk']

question = {
    "question": {
        "bool": {
            "should": [
                {
                    "match": {
                        "document_name": document_name
                    }
                }
            ],
            "ought to": [
                {"term": {"chunk_number": current_chunk - 1}},
                {"term": {"chunk_number": current_chunk + 1}}
            ],
            "minimum_should_match": 1
        }
    }
}

question = """" 
Are you able to record all of the substances within the nuts and seeds granola?
Put the allergens in all caps. 
"""

import json

query_rewriting_prompt = """
Rewrite the question as a json with the next keys:
- rewritten_query: a greater model of the person's question that will probably be used to compute 
an embedding and do semantic search
- key phrases: a listing of key phrases that correspond to the question, for use in a 
search engine, it shouldn't include the product identify.
- product_name: if the question is a a few particular product, give the identify right here,
 in any other case say None.


H: what are the ingedients within the savory path combine?
A: {{
  "rewritten_query": "substances savory path combine",
  "key phrases": ["ingredients"],
  "product_name": "savory path combine"
}}



{question}


Solely output the json, nothing else.
"""

def rewrite_query(question):
    response = call_FM(query_rewriting_prompt.format(question=question))
    print(response)
    json_query = json.masses(response)
    return json_query
    
rewrite_query(question)

{ 
"rewritten_query":"substances nuts and seeds granola allergens",
"key phrases": ["ingredients", "allergens"], 
"product_name": "nuts and seeds granola" 
}

oss = get_opensearch_serverless_client()
request = {
"product_info": product_info, # full textual content for the product data
"vector_field_product":embed_query_titan(product_info), # embedding for product data
"product_name": product_name,
"date": date, # non-obligatory subject, can permit to kind by most up-to-date
"_op_type": "index",
"supply": file_key # that is the s3 location, you'll be able to change this with a URL
}
oss.index(index = index_name, physique = request)

question = """
Are you able to record all of the substances within the nuts and seeds granola?
Put the allergens in daring and all caps.
"""
# utilizing the rewrite_query perform from the earlier part
json_query = rewrite_query(question) 

# get the product identify and key phrases from the json question
product_name = json_query["product_name"] 
key phrases = json_query["keywords"]

# compute the vector embedding of the rewritten question
vector_embedding = compute_embedding(json_query["rewritten_query"])

#initialize search question dictionary
search_query = {"dimension":10, "question": { "bool": { "ought to":[] , "should":[] } } }
# add should with match_phrase clause to filter on product identify
search_query['query']['bool']['should'].append(
    {"match_phrase": {
            "product_name": product_name # Extracted product identify should match product identify subject 
        }
        }

# semantic search
search_query['query']['bool']['should'].append(
        {"function_score": 
            { "question": 
            {"knn": 
            {"vector_field_product": 
            {"vector": vector_embedding, 
            "ok": 10 # The variety of nearest neighbors to retrieve
            }}}, 
            "weight": semantic_weight } })
            
# key phrase search
search_query['query']['bool']['should'].append(
{"function_score": 
        { "question": 
            {"match": 
            # This can improve the rating of chunks that match the phrases within the question
            {"product_info":  question} 
            },
            "weight": keyword_weight } })

# Notice: The scouting stories for Participant A and Participant B used within the instance under
# had been generated by Anthropic’s Claude Sonnet 3.
quotes_tags_prompt = """
You might be an Ai assistant chatbot designed to reply questions on your staff's baseballe scouting stories.

Listed here are some stories about gamers that you should utilize to reply the query:


{doc_0}



{doc_1}



- In  tags, you must put the doc names and quotes from these paperwork 
 that aid you reply this query. 
 You need to format this as a number of jsons format with 'document_name' and 'quote' as keys. 
- Then put your reply in  tags. 
 For those who check with paperwork in your reply, be sure to are utilizing the corresponding tag 
 e.g. in doc_0, in doc_3 and so on.
- If you cannot reply the query as a result of there's not sufficient data within the stories say 
 "I am unable to reply this based mostly on the supplied stories." 



{query}

"""

"""

[
{
"document_name": "doc_0",
"quote": "The main concern with Player A is his approach at the plate. He can be overly aggressive at times and will chase pitches out of the zone. Improving his plate discipline and pitch recognition will be key to him reaching his full offensive potential."
},
{
"document_name": "doc_1",
"quote": "The main area of focus for Player B's development will be improving his plate discipline and pitch recognition. He can be overly aggressive at times, leading to a high strikeout rate and a lower on-base percentage than his hit tool would suggest."
}
]


The principle weaknesses of the gamers are:
For Participant A:
- Overly aggressive method on the plate, chasing pitches out of the zone
- Wants to enhance plate self-discipline and pitch recognition to achieve full offensive potential
For Participant B:
- May be overly aggressive on the plate, resulting in excessive strikeout fee and decrease on-base share
- Wants to enhance plate self-discipline and pitch recognition

"""

# Notice: The scouting stories for Participant A used within the instance under
# had been generated by Anthropic’s Claude Sonnet 3.

quotes_in_text_prompt = """
You might be an Ai assistant chatbot designed to reply questions on your staff's baseballe scouting stories.

Listed here are some stories about gamers that you should utilize to reply the query:


{doc_0}


...


{doc_10}



- Put your reply in  tags.
- Use as a lot data from completely different stories as attainable.
- It's best to solely use data within the paperwork to reply. If you do not have sufficient data within the stories to reply, say you'll be able to't reply based mostly on the stories.
- It's best to floor your reply by quoting the related paperwork by utilizing citation marks.
- After the quotes, put an inline quotation Participant A is "very athletic" (doc_2)



{query}

"""

Beneath is the FM response to the query "What are the strengths of participant A?":

"""

[
{
"document_name": "doc_0",
"quote": "The main concern with Player A is his approach at the plate. He can be overly aggressive at times and will chase pitches out of the zone. Improving his plate discipline and pitch recognition will be key to him reaching his full offensive potential."
},
{
"document_name": "doc_1",
"quote": "The main area of focus for Player B's development will be improving his plate discipline and pitch recognition. He can be overly aggressive at times, leading to a high strikeout rate and a lower on-base percentage than his hit tool would suggest."
}
]


The principle weaknesses of the gamers are:
For Participant A:
- Overly aggressive method on the plate, chasing pitches out of the zone
- Wants to enhance plate self-discipline and pitch recognition to achieve full offensive potential
For Participant B:
- May be overly aggressive on the plate, resulting in excessive strikeout fee and decrease on-base share
- Wants to enhance plate self-discipline and pitch recognition

"""