bioguider 0.2.7__tar.gz → 0.2.8__tar.gz

{bioguider-0.2.7 → bioguider-0.2.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: bioguider
-Version: 0.2.7
+Version: 0.2.8
 Summary: An AI-Powered package to help biomedical developers to generate clear documentation
 License: MIT
 Author: Cankun Wang

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/agents/agent_tools.py

@@ -53,7 +53,8 @@ Returns:
 class summarize_file_tool(agent_tool):
     """ read and summarize the file
 Args:
-    file_path str: file path
+    file_path str [required]: the file path
+    summarize_prompt str [required]: a prompt to guide how to summarize the file, if no prompt needed, please set "N/A"
 Returns:
     A string of summarized file content, if the file does not exist, return None.         
         """
@@ -75,27 +76,31 @@ Returns:
         self.summary_file_db = db
         self.summarize_instruction = summaize_instruction
 
-    def _retrive_from_summary_file_db(self, file_path: str) -> str | None:
+    def _retrive_from_summary_file_db(self, file_path: str, prompt: str = "N/A") -> str | None:
         if self.summary_file_db is None:
             return None
         return self.summary_file_db.select_summarized_text(
             file_path=file_path,
             instruction=self.summarize_instruction,
             summarize_level=self.detailed_level,
+            summarize_prompt=prompt,
         )
-    def _save_to_summary_file_db(self, file_path: str, summarized_text: str, token_usage: dict):
+    def _save_to_summary_file_db(self, file_path: str, prompt: str, summarized_text: str, token_usage: dict):
         if self.summary_file_db is None:
             return
         self.summary_file_db.upsert_summarized_file(
             file_path=file_path,
             instruction=self.summarize_instruction,
             summarize_level=self.detailed_level,
+            summarize_prompt=prompt,
             summarized_text=summarized_text,
             token_usage=token_usage,
         )
-    def run(self, file_path: str) -> str | None:
+    def run(self, file_path: str, summarize_prompt: str) -> str | None:
         if file_path is None:
             return None
+        if summarize_prompt is None or len(summarize_prompt) == 0:
+            summarize_prompt = "N/A"
             
         file_path = file_path.strip()
         abs_file_path = file_path
@@ -104,7 +109,8 @@ Returns:
         if not os.path.isfile(abs_file_path):
             return f"{file_path} is not a file."
         summarized_content = self._retrive_from_summary_file_db(
-            file_path=file_path
+            file_path=file_path,
+            prompt=summarize_prompt,
         )
         if summarized_content is not None:
             return f"summarized content of file {file_path}: " + summarized_content
@@ -114,9 +120,11 @@ Returns:
         summarized_content, token_usage = summarize_file(
             self.llm, abs_file_path, file_content, self.detailed_level,
             summary_instructions=self.summarize_instruction,
+            summarize_prompt=summarize_prompt,
         )
         self._save_to_summary_file_db(
             file_path=file_path,
+            prompt=summarize_prompt,
             summarized_text=summarized_content,
             token_usage=token_usage,
         )

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/agents/agent_utils.py

@@ -153,13 +153,28 @@ def read_directory(
 
 
 EVALUATION_SUMMARIZE_FILE_PROMPT = ChatPromptTemplate.from_template("""
-You are provided with the content of the file **{file_name}**:  
-```
-{file_content}
-```
+You will be provided with the content of the file **{file_name}**:  
+
+---
+
 ### **Summary Instructions**
 {summary_instructions}
 The content is lengthy. Please generate a concise summary ({sentence_num1}-{sentence_num2} sentences).
+
+---
+
+### **Important Instructions**
+{summarize_prompt}
+
+---
+
+### **File Content**
+Here is the file content:
+{file_content}
+
+---
+
+Now, let's start to summarize.
 """)
 
 MAX_FILE_LENGTH=20 *1024 # 20K
@@ -170,6 +185,7 @@ def summarize_file(
     content: str | None = None, 
     level: int = 3,
     summary_instructions: str | None = None,
+    summarize_prompt: str = "N/A",
     db: SummarizedFilesDb | None = None,
 ) -> Tuple[str, dict]:
     if content is None:
@@ -198,6 +214,7 @@ def summarize_file(
         summary_instructions=summary_instructions \
             if summary_instructions is not None and len(summary_instructions) > 0 \
             else "N/A",
+        summarize_prompt=summarize_prompt,
     )
     
     config = {"recursion_limit": 500}
@@ -210,7 +227,12 @@ def summarize_file(
     }
     if db is not None:
         db.upsert_summarized_file(
-            name, summary_instructions, level, token_usage
+            file_path=name,
+            instruction=summary_instructions,
+            summarize_level=level,
+            summarize_prompt=summarize_prompt,
+            summarized_text=out,
+            token_usage=token_usage,
         )
     
     return out, token_usage

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/agents/collection_execute_step.py

@@ -62,11 +62,13 @@ Action Observation: {{Observation2}}
 ```
 Action: summarize_file_tool  
 Action Input: README.md  
+Action Input: "Please extract license information in summarized file content."
 Observation: # BioGuider\nBioGuider is a Python package for bioinformatics.\n...
 ...
 Final Answer:
 Action: summarize_file_tool
 Action Input: README.md
+Action Input: "N/A"
 Action Observation: # BioGuider\nBioGuider is a Python package for bioinformatics.\n...
 ---
 Action: check_file_related_tool

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/agents/collection_task.py

@@ -61,6 +61,46 @@ class CollectionTask(AgentTask):
         self.tools: list[any] | None = None
         self.custom_tools: list[Tool] | None = None
 
+    def _prepare_tools(self, related_file_goal_item_desc):
+        tool_rd = read_directory_tool(repo_path=self.repo_path)
+        tool_sum = summarize_file_tool(
+            llm=self.llm,
+            repo_path=self.repo_path,
+            output_callback=self.step_callback,
+            db=self.summary_file_db,
+        )
+        tool_rf = read_file_tool(repo_path=self.repo_path)
+        tool_cf = check_file_related_tool(
+            llm=self.llm,
+            repo_path=self.repo_path,
+            goal_item_desc=related_file_goal_item_desc,
+            output_callback=self.step_callback,
+        )
+        self.tools = [tool_rd, tool_sum, tool_rf, tool_cf]
+        self.custom_tools = [
+            Tool(
+                name = tool_rd.__class__.__name__,
+                func = tool_rd.run,
+                description=tool_rd.__class__.__doc__,
+            ),
+            StructuredTool.from_function(
+                tool_sum.run,
+                description=tool_sum.__class__.__doc__,
+                name=tool_sum.__class__.__name__,
+            ),
+            Tool(
+                name = tool_rf.__class__.__name__,
+                func = tool_rf.run,
+                description=tool_rf.__class__.__doc__,
+            ),
+            Tool(
+                name = tool_cf.__class__.__name__,
+                func = tool_cf.run,
+                description=tool_cf.__class__.__doc__,
+            ),
+        ]
+        self.custom_tools.append(CustomPythonAstREPLTool())
+
     def _initialize(self):
         # initialize the 2-level file structure of the repo
         if not os.path.exists(self.repo_path):
@@ -76,28 +116,8 @@ class CollectionTask(AgentTask):
             goal_item=collection_item["goal_item"],
             related_file_description=collection_item["related_file_description"],
         )
-        self.tools = [
-            read_directory_tool(repo_path=self.repo_path),
-            summarize_file_tool(
-                llm=self.llm,
-                repo_path=self.repo_path,
-                output_callback=self.step_callback,
-                db=self.summary_file_db,
-            ),
-            read_file_tool(repo_path=self.repo_path),
-            check_file_related_tool(
-                llm=self.llm,
-                repo_path=self.repo_path,
-                goal_item_desc=related_file_goal_item_desc,
-                output_callback=self.step_callback,
-            ),
-        ]
-        self.custom_tools = [Tool(
-            name=tool.__class__.__name__,
-            func=tool.run,
-            description=tool.__class__.__doc__,
-        ) for tool in self.tools]
-        self.custom_tools.append(CustomPythonAstREPLTool())
+        
+        self._prepare_tools(related_file_goal_item_desc)
         self.steps = [
             CollectionPlanStep(
                 llm=self.llm,

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/agents/evaluation_installation_task.py

@@ -118,6 +118,7 @@ class EvaluationInstallationTask(EvaluationTask):
         step_callback = None,
     ):
         super().__init__(llm, repo_path, gitignore_path, meta_data, step_callback)
+        self.evaluation_name = "Installation Evaluation"
 
     def _evaluate(self, files: list[str] | None = None):
         if files is None or len(files) == 0:

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/agents/identification_execute_step.py

@@ -60,11 +60,13 @@ Action Observation: {{Observation2}}
 ```
 Action: summarize_file_tool  
 Action Input: README.md  
+Action Input: "Please extract license information in summarized file content."
 Observation: # BioGuider\nBioGuider is a Python package for bioinformatics.\n...
 ...
 Final Answer:
 Action: summarize_file_tool
 Action Input: README.md
+Action Input: "N/A"
 Action Observation: # BioGuider\nBioGuider is a Python package for bioinformatics.\n...
 ---
 Action: check_file_related_tool

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/agents/identification_task.py

@@ -6,7 +6,7 @@ from enum import Enum
 from typing import Callable
 from pydantic import BaseModel, Field
 from langchain_openai.chat_models.base import BaseChatOpenAI
-from langchain.tools import Tool
+from langchain.tools import Tool, StructuredTool
 from langgraph.graph import StateGraph, START, END
 
 from bioguider.utils.constants import PrimaryLanguageEnum, ProjectTypeEnum
@@ -72,6 +72,36 @@ class IdentificationTask(AgentTask):
         self.custom_tools = []
         self.steps: list[PEOCommonStep] = []
 
+    def _prepare_tools(self):
+        tool_rd = read_directory_tool(repo_path=self.repo_path)
+        tool_sum = summarize_file_tool(
+            llm=self.llm,
+            repo_path=self.repo_path,
+            output_callback=self.step_callback,
+            db=self.summary_file_db,
+        )
+        tool_rf = read_file_tool(repo_path=self.repo_path)
+        
+        self.tools = [tool_rd, tool_sum, tool_rf,]
+        self.custom_tools = [
+            Tool(
+                name = tool_rd.__class__.__name__,
+                func = tool_rd.run,
+                description=tool_rd.__class__.__doc__,
+            ),
+            StructuredTool.from_function(
+                tool_sum.run,
+                description=tool_sum.__class__.__doc__,
+                name=tool_sum.__class__.__name__,
+            ),
+            Tool(
+                name = tool_rf.__class__.__name__,
+                func = tool_rf.run,
+                description=tool_rf.__class__.__doc__,
+            ),
+        ]
+        self.custom_tools.append(CustomPythonAstREPLTool())
+
     def _initialize(self):        
         if not os.path.exists(self.repo_path):
             raise ValueError(f"Repository path {self.repo_path} does not exist.")
@@ -81,22 +111,7 @@ class IdentificationTask(AgentTask):
         for f, f_type in file_pairs:
             self.repo_structure += f"{f} - {f_type}\n"
 
-        self.tools = [
-            summarize_file_tool(
-                llm=self.llm, 
-                repo_path=self.repo_path, 
-                output_callback=self._print_step,
-                db=self.summary_file_db,
-            ),
-            read_directory_tool(repo_path=self.repo_path, gitignore_path=self.gitignore_path),
-            read_file_tool(repo_path=self.repo_path),
-        ]
-        self.custom_tools = [Tool(
-            name=tool.__class__.__name__,
-            func=tool.run,
-            description=tool.__class__.__doc__,
-        ) for tool in self.tools]
-        self.custom_tools.append(CustomPythonAstREPLTool())
+        self._prepare_tools()
         self.steps = [
             IdentificationPlanStep(
                 llm=self.llm,

{bioguider-0.2.7 → bioguider-0.2.8}/bioguider/database/summarized_file_db.py

@@ -18,22 +18,23 @@ summarized_files_create_table_query = f"""
 CREATE TABLE IF NOT EXISTS {SUMMARIZED_FILES_TABLE_NAME} (
     file_path VARCHAR(512),
     instruction TEXT,
+    summarize_prompt TEXT,
     summarize_level INTEGER,
     summarized_text TEXT,
     token_usage  VARCHAR(512),
     datetime TEXT NOT NULL DEFAULT (strftime('%Y-%m-%d %H:%M:%f', 'now')),
-    UNIQUE (file_path, instruction, summarize_level)
+    UNIQUE (file_path, instruction, summarize_level, summarize_prompt)
 );
 """
 summarized_files_upsert_query = f"""
-INSERT INTO {SUMMARIZED_FILES_TABLE_NAME}(file_path, instruction, summarize_level, summarized_text, token_usage, datetime)
-VALUES (?, ?, ?, ?, ?, strftime('%Y-%m-%d %H:%M:%f', 'now'))
-ON CONFLICT(file_path, instruction, summarize_level) DO UPDATE SET summarized_text=excluded.summarized_text,
+INSERT INTO {SUMMARIZED_FILES_TABLE_NAME}(file_path, instruction, summarize_level, summarize_prompt, summarized_text, token_usage, datetime)
+VALUES (?, ?, ?, ?, ?, ?, strftime('%Y-%m-%d %H:%M:%f', 'now'))
+ON CONFLICT(file_path, instruction, summarize_level, summarize_prompt) DO UPDATE SET summarized_text=excluded.summarized_text,
 datetime=strftime('%Y-%m-%d %H:%M:%f', 'now');
 """
 summarized_files_select_query = f"""
 SELECT summarized_text, datetime FROM {SUMMARIZED_FILES_TABLE_NAME} 
-where file_path = ? and instruction = ? and summarize_level = ?;
+where file_path = ? and instruction = ? and summarize_level = ? and summarize_prompt=?;
 """
 
 class SummarizedFilesDb:
@@ -83,6 +84,7 @@ class SummarizedFilesDb:
         file_path: str,
         instruction: str,
         summarize_level: int,
+        summarize_prompt: str,
         summarized_text: str,
         token_usage: dict | None = None
     ):
@@ -96,7 +98,7 @@ class SummarizedFilesDb:
             cursor = self.connection.cursor()
             cursor.execute(
                 summarized_files_upsert_query, 
-                (file_path, instruction, summarize_level, summarized_text, token_usage, )
+                (file_path, instruction, summarize_level, summarize_prompt, summarized_text, token_usage, )
             )
             self.connection.commit()
             return True
@@ -112,6 +114,7 @@ class SummarizedFilesDb:
         file_path: str,
         instruction: str,
         summarize_level: int,
+        summarize_prompt: str,
     ) -> str | None:
         self._connect_to_db()
         self._ensure_tables()
@@ -119,7 +122,7 @@ class SummarizedFilesDb:
             cursor = self.connection.cursor()
             cursor.execute(
                 summarized_files_select_query, 
-                (file_path, instruction, summarize_level,)
+                (file_path, instruction, summarize_level, summarize_prompt,)
             )
             row = cursor.fetchone()
             if row is None:

{bioguider-0.2.7 → bioguider-0.2.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "bioguider"
-version = "0.2.7"
+version = "0.2.8"
 description = "An AI-Powered package to help biomedical developers to generate clear documentation"
 authors = [
     "Cankun Wang <Cankun.Wang@osumc.edu>",