create get_gene_id and get_gene_location tools

app.py

@@ -6,31 +6,67 @@ import yaml
 from tools.final_answer import FinalAnswerTool
 
 from Gradio_UI import GradioUI
+import xml.etree.ElementTree as ET
+
+base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
 
 @tool
-def my_custom_tool(arg1:str, arg2:int)-> str: 
-    """A tool that does nothing yet 
+def get_gene_id(organism:str, gene:int) -> str: 
+    """A tool that gets the gene ID from an organism with the provided gene name
     Args:
-        arg1: the first argument
-        arg2: the second argument
+        organism: the name of the organism
+        gene: the name of the gene
     """
-    return "What magic will you build ?"
+    search_params = {
+        "db": "gene",
+        "term": f"{gene}[Gene Name] AND {organism}[Organism]",
+        "retmode": "xml",
+    }
+    esearch_url = base_url + "esearch.fcgi"
+    esearch_response = requests.get(esearch_url, params=search_params)
+    esearch_tree = ET.fromstring(esearch_response.text)
+    id_list = esearch_tree.find("IdList")
+    
+    if id_list is None or len(id_list) == 0:
+        return "Gene not found."
+
+    return id_list.find("Id").text
 
 @tool
-def get_current_time_in_timezone(timezone: str) -> str:
-    """A tool that fetches the current local time in a specified timezone.
+def get_gene_location(gene_id:str) -> str:
+    """A tool that gets the gene location from a gene ID
     Args:
-        timezone: A string representing a valid timezone (e.g., 'America/New_York').
+        gene_id: the gene ID
     """
+    efetch_url = base_url + "efetch.fcgi"
+    fetch_params = {
+        "db": "gene",
+        "id": gene_id,
+        "retmode": "xml",
+    }
+    efetch_response = requests.get(efetch_url, params=fetch_params)
+    fetch_tree = ET.fromstring(efetch_response.text)
+
+    # Parse XML to extract chromosome, start, end
     try:
-        # Create timezone object
-        tz = pytz.timezone(timezone)
-        # Get current time in that timezone
-        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
-        return f"The current local time in {timezone} is: {local_time}"
-    except Exception as e:
-        return f"Error fetching time for timezone '{timezone}': {str(e)}"
+        chr_elem = fetch_tree.find(".//Gene-ref_maploc")
+        chromosome = chr_elem.text if chr_elem is not None else "Unknown"
 
+        interval = fetch_tree.find(".//Seq-interval")
+        start = int(interval.find("Seq-interval_from").text) + 1
+        end = int(interval.find("Seq-interval_to").text) + 1
+
+        strand_elem = interval.find("Seq-interval_strand/Na-strand/value")
+        strand = strand_elem.text if strand_elem is not None else "unknown"
+
+        return {
+            "chromosome": chromosome,
+            "start": start,
+            "end": end,
+            "strand": strand
+        }
+    except Exception as e:
+        return "Error parsing gene location:", str(e)
 
 final_answer = FinalAnswerTool()
 
@@ -38,22 +74,18 @@ final_answer = FinalAnswerTool()
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
 
 model = HfApiModel(
-max_tokens=2096,
-temperature=0.5,
-model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-custom_role_conversions=None,
+    max_tokens=2096,
+    temperature=0.5,
+    model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
+    custom_role_conversions=None,
 )
 
-
-# Import tool from Hub
-image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
-
 with open("prompts.yaml", 'r') as stream:
     prompt_templates = yaml.safe_load(stream)
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer, image_generation_tool, get_current_time_in_timezone], ## add your tools here (don't remove final answer)
+    tools=[final_answer, get_gene_id, get_gene_location],
     max_steps=6,
     verbosity_level=1,
     grammar=None,