1
# Uncomment if you need to install the following packages
2
# !pip install cohere
3
# !pip install python-dotenv
4
# !pip install pandas

1
import os
2
import json
3
import re
4
import getpass
5
from langchain.agents import AgentExecutor
6
from langchain_cohere.chat_models import ChatCohere
7
from langchain_cohere.react_multi_hop.agent import create_cohere_react_agent
8
from langchain_core.prompts import ChatPromptTemplate
9
from langchain_core.pydantic_v1 import BaseModel, Field
10
from langchain_core.tools import tool

1
# load the cohere api key
2
os.environ["COHERE_API_KEY"] = getpass.getpass()

1
@tool
2
def regex_extractor(user_query: str) -> dict:
3
    """Function which, given the query from the user, returns a dictionary parameter:value."""
4
    uuid = re.findall("\s([a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})", user_query)
5
    nmgs = re.findall("(0000[A-Z0-9]{21})", user_query)
6
    objref = re.findall("\s([A-Z]{5,9}\d{3,4}[A-Z]{3,8})", user_query)
7
    urn = re.findall("urn:[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}",user_query,)
8
    d = {"uuid": uuid,
9
         "nmgs": nmgs,
10
         "objref": objref,
11
         "urn": urn}
12
    d_filtered = {k: v for k, v in d.items() if v != []}
13
    return d_filtered
14
15
class extract_code_v1productssearch(BaseModel):
16
    user_query: str = Field(
17
        description="This is the full input query as received from the user. Do not truncate or modify the query in any way."
18
    )
19
regex_extractor.name = "regex_extractor"
20
regex_extractor.args_schema = extract_code_v1productssearch
21
tools=[regex_extractor]

1
# Let's define the system instruction (preamble) for the Agent.
2
# The system instruction includes info about:
3
# - the tool the Agent has access to
4
# - the cases in which the Agent has to produce an output without using the tool
5
# - some examples to clarify the task
6
preamble = """You are an assistant that given a user's query about, generates a request an API.
7
You can use the tool named "regex_extractor".
8
Pass to the "regex_extractor" tool the entire text of the the input query.
9
The tool returns a dictionary, in which keys are the name of the codes, and values a list of extracted codes.
10
Create a JSON for each of the key-value pairs in the dictionary.
11
12
Return a list of JSONs. Make sure each JSON is properly defined. Do not return any other explanation or comment.
13
You MUST generate a perfect JSON object: make sure that each string in the lists is included between quotes.
14
15
If the request mentions one of the tags listed below, or a related word, create a dictionary in which the key is "taxonomies" and the value the list of capitalized tags.
16
Tags list: cars, trucks, clothes, sport
17
18
19
Find a list of examples here:
20
User question | parameter for the tool | what you should understand
21
Look products GLCMS004AGTCAMIS; 0000234GLCMS0100ANORAKCAA, GLCHL000CGUCHALE | Look products GLCMS004AGTCAMIS; 0000234GLCMS0100ANORAKCAA, GLCHL000CGUCHALE | [{"objref":["GLCMS004AGTCAMIS","GLCHL000CGUCHALE"]},{"nmgs":["0000234GLCMS0100ANORAKCAA"]}]
22
Retrieve id 7410e652-639d-402e-984e-8fd7025f0aac 8bb21b93-2ddf-4a63-af63-ddb6b1be49a1, ref GLPNT0005GUJOGGE GLSBR000BGASOBRE, nmg 0000234GLCHL0200ARTINDIUS | Retrieve id 7410e652-639d-402e-984e-8fd7025f0aac 8bb21b93-2ddf-4a63-af63-ddb6b1be49a1, ref GLPNT0005GUJOGGE GLSBR000BGASOBRE, nmg 0000234GLCHL0200ARTINDIUS | [{"uuid":["7410e652-639d-402e-984e-8fd7025f0aac","8bb21b93-2ddf-4a63-af63-ddb6b1be49a1"]}, {"objref":["GLPNT0005GUJOGGE","GLSBR000BGASOBRE"]},{"nmgs":["0000234GLCHL0200ARTINDIUS"]}]
23
Look for items of cars and trucks | Look for items of pants and t-shirts | [{'taxonomies': ['CARS', 'TRUCKS']}]
24
Search products sport | Search products dress and jumpsuit | [{'taxonomies': ['SPORT']}]
25
"""

1
# Define the prompt
2
prompt = ChatPromptTemplate.from_template("{input}")
3
# Define the agent
4
llm = ChatCohere(model="command-a-03-2025", temperature=0)
5
# instantiate agent and agent executor
6
agent = create_cohere_react_agent(
7
   llm=llm,
8
   tools=tools,
9
   prompt=prompt,
10
)
11
agent_executor = AgentExecutor(agent=agent,
12
                               tools=tools,
13
                               verbose=True,
14
                               return_intermediate_steps=True
15
                    )

1
# finally, let's write a function to convert the Agents output to a json
2
def convert_to_json(string: str) -> json:
3
    return json.loads(
4
                string.replace("\xa0", " ")
5
                .replace("json", "")
6
                .replace("`", "")
7
                .replace("`", "")
8
            )

1
query_1 = "Look for urn:75f2b737-06dd-4399-9206-a6c11b65138e, GLCMS004AGTCAMIS; 0000234GLCMS0100ANORAKCAA, GLCHL000CGUCHALE"
2
response_1 = agent_executor.invoke(
3
            {
4
                "input": query_1,
5
                "preamble": preamble,
6
            }
7
        )

> Entering new AgentExecutor chain...

I will use the regex_extractor tool to extract the codes from the user query.
{'tool_name': 'regex_extractor', 'parameters': {'user_query': 'Look for urn:75f2b737-06dd-4399-9206-a6c11b65138e, GLCMS004AGTCAMIS; 0000234GLCMS0100ANORAKCAA, GLCHL000CGUCHALE'}}
{'nmgs': ['0000234GLCMS0100ANORAKCAA'], 'objref': ['GLCMS004AGTCAMIS', 'GLCHL000CGUCHALE'], 'urn': ['urn:75f2b737-06dd-4399-9206-a6c11b65138e']}Relevant Documents: 0
Cited Documents: 0
Answer: ```json JSON
[
    {
        "urn": ["urn:75f2b737-06dd-4399-9206-a6c11b65138e"],
        "objref": ["GLCMS004AGTCAMIS", "GLCHL000CGUCHALE"],
        "nmgs": ["0000234GLCMS0100ANORAKCAA"]
    }
]
```
Grounded answer: ```json JSON
  [
    {
        "urn": [<co: 0>"urn:75f2b737-06dd-4399-9206-a6c11b65138e</co: 0>"],
        "objref": [<co: 0>"GLCMS004AGTCAMIS</co: 0>", <co: 0>"GLCHL000CGUCHALE</co: 0>"],
        "nmgs": [<co: 0>"0000234GLCMS0100ANORAKCAA</co: 0>"]
    }
]
```
> Finished chain.

1
# let's have a look at the final output
2
convert_to_json(response_1['output'])

1
[{'urn': ['urn:75f2b737-06dd-4399-9206-a6c11b65138e'],
2
  'objref': ['GLCMS004AGTCAMIS', 'GLCHL000CGUCHALE'],
3
  'nmgs': ['0000234GLCMS0100ANORAKCAA']}]

1
query_2 = "I need tennis products"
2
3
response_2 = agent_executor.invoke(
4
    {
5
        "input": query_2,
6
        "preamble": preamble,
7
    }
8
)

> Entering new AgentExecutor chain...

I will use the regex_extractor tool to extract the relevant information from the user request.
{'tool_name': 'regex_extractor', 'parameters': {'user_query': 'I need tennis products'}}
{}Relevant Documents: None
Cited Documents: None
Answer: ```json JSON
[
    {
        "taxonomies": [
            "SPORT"
        ]
    }
]
```
Grounded answer: ```json JSON
  [
  {
  "taxonomies": [
  "SPORT"
  ]
  }
]
```
> Finished chain.

1
convert_to_json(response_2['output'])

1
[{'taxonomies': ['SPORT']}]

1
query_3 = "Look for GLBRL0000GACHALE, nmg 0000234GLCZD0000GUREDTOAA and car products"
2
3
response_3 = agent_executor.invoke(
4
    {
5
        "input": query_3,
6
        "preamble": preamble,
7
    }
8
)

> Entering new AgentExecutor chain...

I will use the regex_extractor tool to extract the codes from the user query. Then, I will create a JSON for each of the key-value pairs in the dictionary.
{'tool_name': 'regex_extractor', 'parameters': {'user_query': 'Look for GLBRL0000GACHALE, nmg 0000234GLCZD0000GUREDTOAA and car products'}}
{'nmgs': ['0000234GLCZD0000GUREDTOAA'], 'objref': ['GLBRL0000GACHALE']}Relevant Documents: 0
Cited Documents: 0
Answer: ```json JSON
[
    {
        "objref": ["GLBRL0000GACHALE"],
        "nmgs": ["0000234GLCZD0000GUREDTOAA"]
    },
    {
        "taxonomies": ["CARS"]
    }
]
```
Grounded answer: ```json JSON
  [
    {
        "objref": [<co: 0>"GLBRL0000GACHALE</co: 0>"],
        "nmgs": [<co: 0>"0000234GLCZD0000GUREDTOAA</co: 0>"]
    },
    {
        "taxonomies": ["CARS"]
    }
]
```
> Finished chain.

1
convert_to_json(response_3['output'])

1
[{'objref': ['GLBRL0000GACHALE'], 'nmgs': ['0000234GLCZD0000GUREDTOAA']},
2
  {'taxonomies': ['CARS']}]