edit secret key

Promptless_LLM_Agent.py

@@ -1,64 +1,65 @@
-# Warning control
-import warnings
-warnings.filterwarnings('ignore')
-
-from typing import List
-import json
-from pydantic import BaseModel
-# from langchain_community.llms import HuggingFaceHub
-from langchain_huggingface import HuggingFaceEndpoint
-from crewai import Agent, Task, Crew
-
-import os
-from dotenv import load_dotenv, find_dotenv
-_ = load_dotenv(find_dotenv()) # read local .env file
-hf_api_key = os.environ['HF_API_KEY']
-
-llm = HuggingFaceEndpoint(
-    repo_id="HuggingFaceH4/zephyr-7b-beta",
-    huggingfacehub_api_token=hf_api_key,
-    task="text-generation"
-)
-
-graphicDesigner = Agent(
-    role="Graphic Designer",
-    goal="Provide the list of relevant questions that can be ask to user based on his/her requirement: {requirement}",
-    backstory="You're working as expert graphic designer "
-              "A user has shared with you the requirement: {requirement}."
-              "Use information present in requirement"
-              "and provide the list of questions that can be asked to user"
-              "to gather more specific information based on requirement",
-    llm=llm,
-    allow_delegation=False,
-	verbose=False
-)
-
-class Questions(BaseModel):
-    QuestionsList: List[str]
-
-Ask_questions = Task(
-    description=(
-        "Provide the list of relevant questions that can be ask to user to gather more specific information based on requirement: {requirement}"
-    ),
-    expected_output="List of relevant questions based on user requirement. output only questions",
-    # output_json=Questions,
-    agent=graphicDesigner,
-)
-
-crew = Crew(
-    agents=[graphicDesigner],
-    tasks=[Ask_questions],
-    verbose=False
-)
-
-def questions(requirement, userDefinedQuestions=None):
-    # "I want a logo for my new business."
-
-    if not userDefinedQuestions:
-        result = crew.kickoff(inputs={"requirement": requirement})
-        result = result.split('\n')
-        # json_dict = json.loads(result)
-        questions = [i.split('. ')[1] for i in result]
-        return questions
-    else:
+# Warning control
+import warnings
+warnings.filterwarnings('ignore')
+
+from typing import List
+import json
+from pydantic import BaseModel
+# from langchain_community.llms import HuggingFaceHub
+from langchain_huggingface import HuggingFaceEndpoint
+from crewai import Agent, Task, Crew
+
+import os
+from dotenv import load_dotenv, find_dotenv
+_ = load_dotenv(find_dotenv()) # read local .env file
+# hf_api_key = os.environ['HF_API_KEY']
+hf_api_key = os.getenv('HF_API_KEY')
+
+llm = HuggingFaceEndpoint(
+    repo_id="HuggingFaceH4/zephyr-7b-beta",
+    huggingfacehub_api_token=hf_api_key,
+    task="text-generation"
+)
+
+graphicDesigner = Agent(
+    role="Graphic Designer",
+    goal="Provide the list of relevant questions that can be ask to user based on his/her requirement: {requirement}",
+    backstory="You're working as expert graphic designer "
+              "A user has shared with you the requirement: {requirement}."
+              "Use information present in requirement"
+              "and provide the list of questions that can be asked to user"
+              "to gather more specific information based on requirement",
+    llm=llm,
+    allow_delegation=False,
+	verbose=False
+)
+
+class Questions(BaseModel):
+    QuestionsList: List[str]
+
+Ask_questions = Task(
+    description=(
+        "Provide the list of relevant questions that can be ask to user to gather more specific information based on requirement: {requirement}"
+    ),
+    expected_output="List of relevant questions based on user requirement. output only questions",
+    # output_json=Questions,
+    agent=graphicDesigner,
+)
+
+crew = Crew(
+    agents=[graphicDesigner],
+    tasks=[Ask_questions],
+    verbose=False
+)
+
+def questions(requirement, userDefinedQuestions=None):
+    # "I want a logo for my new business."
+
+    if not userDefinedQuestions:
+        result = crew.kickoff(inputs={"requirement": requirement})
+        result = result.split('\n')
+        # json_dict = json.loads(result)
+        questions = [i.split('. ')[1] for i in result]
+        return questions
+    else:
         return userDefinedQuestions