Bot Files
Browse files- .env +1 -0
- README.md +5 -9
- app.py +292 -0
- chat_history.json +121 -0
- requirements.txt +6 -0
.env
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
GEMINI_API_KEY=AIzaSyCZtDtt7K6g3IgR0GsQ2pil4xsu7Jrt_lk
|
README.md
CHANGED
@@ -1,12 +1,8 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 5.31.0
|
8 |
app_file: app.py
|
9 |
-
|
10 |
-
---
|
11 |
-
|
12 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
---
|
2 |
+
title: LangChain Powered ChatBot
|
3 |
+
emoji: 🤖
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: purple
|
6 |
sdk: gradio
|
|
|
7 |
app_file: app.py
|
8 |
+
---
|
|
|
|
|
|
app.py
ADDED
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import uuid
|
3 |
+
import json
|
4 |
+
import time
|
5 |
+
import gradio as gr
|
6 |
+
import logging
|
7 |
+
from dotenv import load_dotenv
|
8 |
+
import google.generativeai as genai
|
9 |
+
|
10 |
+
from langgraph.graph import START, MessagesState, StateGraph
|
11 |
+
from langgraph.checkpoint.memory import MemorySaver
|
12 |
+
from langchain_core.messages import HumanMessage, AIMessage
|
13 |
+
from langchain_core.prompts.chat import (
|
14 |
+
ChatPromptTemplate,
|
15 |
+
SystemMessagePromptTemplate,
|
16 |
+
MessagesPlaceholder,
|
17 |
+
HumanMessagePromptTemplate,
|
18 |
+
)
|
19 |
+
from langchain_google_genai import ChatGoogleGenerativeAI
|
20 |
+
from langchain_core.messages import BaseMessage
|
21 |
+
|
22 |
+
|
23 |
+
# === Logging & .env ===
|
24 |
+
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
|
25 |
+
logger = logging.getLogger(__name__)
|
26 |
+
load_dotenv()
|
27 |
+
|
28 |
+
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
|
29 |
+
if not GEMINI_API_KEY:
|
30 |
+
raise ValueError("Missing GEMINI_API_KEY")
|
31 |
+
genai.configure(api_key=GEMINI_API_KEY)
|
32 |
+
|
33 |
+
HISTORY_FILE = "chat_history.json"
|
34 |
+
|
35 |
+
# === Persistent Storage ===
|
36 |
+
def load_all_sessions():
|
37 |
+
if os.path.exists(HISTORY_FILE):
|
38 |
+
with open(HISTORY_FILE, "r", encoding="utf-8") as f:
|
39 |
+
return json.load(f)
|
40 |
+
return {}
|
41 |
+
|
42 |
+
def save_all_sessions(sessions):
|
43 |
+
with open(HISTORY_FILE, "w", encoding="utf-8") as f:
|
44 |
+
json.dump(sessions, f, indent=2)
|
45 |
+
|
46 |
+
# === Chatbot Class ===
|
47 |
+
class GeminiChatbot:
|
48 |
+
def __init__(self):
|
49 |
+
self.setup_model()
|
50 |
+
|
51 |
+
def setup_model(self):
|
52 |
+
system_template = """
|
53 |
+
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.
|
54 |
+
Your answers should be informative, engaging, and accurate. If a question doesn't make any sense, or isn't factually coherent, explain why instead of answering something not correct.
|
55 |
+
If you don't know the answer to a question, please don't share false information.
|
56 |
+
"""
|
57 |
+
|
58 |
+
self.prompt = ChatPromptTemplate.from_messages([
|
59 |
+
SystemMessagePromptTemplate.from_template(system_template),
|
60 |
+
MessagesPlaceholder(variable_name="chat_history"),
|
61 |
+
HumanMessagePromptTemplate.from_template("{input}")
|
62 |
+
])
|
63 |
+
|
64 |
+
self.model = ChatGoogleGenerativeAI(
|
65 |
+
model="gemini-2.0-flash",
|
66 |
+
temperature=0.7,
|
67 |
+
top_p=0.95,
|
68 |
+
google_api_key=GEMINI_API_KEY,
|
69 |
+
convert_system_message_to_human=True
|
70 |
+
)
|
71 |
+
|
72 |
+
def call_model(state: MessagesState):
|
73 |
+
chat_history = state["messages"][:-1]
|
74 |
+
user_input = state["messages"][-1].content
|
75 |
+
|
76 |
+
formatted_messages = self.prompt.format_messages(
|
77 |
+
chat_history=chat_history,
|
78 |
+
input=user_input
|
79 |
+
)
|
80 |
+
|
81 |
+
response = self.model.invoke(formatted_messages)
|
82 |
+
return {"messages": response}
|
83 |
+
|
84 |
+
workflow = StateGraph(state_schema=MessagesState)
|
85 |
+
workflow.add_node("model", call_model)
|
86 |
+
workflow.add_edge(START, "model")
|
87 |
+
|
88 |
+
self.memory = MemorySaver()
|
89 |
+
self.app = workflow.compile(checkpointer=self.memory)
|
90 |
+
|
91 |
+
def get_response(self, user_message, history, thread_id):
|
92 |
+
try:
|
93 |
+
# Convert string history into LangChain message objects
|
94 |
+
langchain_history = []
|
95 |
+
for user, bot in history:
|
96 |
+
langchain_history.append(HumanMessage(content=user))
|
97 |
+
langchain_history.append(AIMessage(content=bot))
|
98 |
+
|
99 |
+
# Add the new user message
|
100 |
+
input_message = HumanMessage(content=user_message)
|
101 |
+
full_history = langchain_history + [input_message]
|
102 |
+
|
103 |
+
full_response = ""
|
104 |
+
config = {"configurable": {"thread_id": thread_id}}
|
105 |
+
|
106 |
+
# Invoke the model with full conversation
|
107 |
+
response = self.app.invoke({"messages": full_history}, config)
|
108 |
+
complete_response = response["messages"][-1].content
|
109 |
+
|
110 |
+
for char in complete_response:
|
111 |
+
full_response += char
|
112 |
+
yield full_response
|
113 |
+
time.sleep(0.01)
|
114 |
+
|
115 |
+
except Exception as e:
|
116 |
+
logger.error(f"LangGraph Error: {e}")
|
117 |
+
yield f"⚠ Error: {type(e).__name__} — {str(e)}"
|
118 |
+
|
119 |
+
|
120 |
+
# === Gradio UI ===
|
121 |
+
chatbot = GeminiChatbot()
|
122 |
+
sessions = load_all_sessions()
|
123 |
+
|
124 |
+
|
125 |
+
def launch_interface():
|
126 |
+
with gr.Blocks(
|
127 |
+
theme=gr.themes.Base(),
|
128 |
+
css="""
|
129 |
+
body {
|
130 |
+
background-color: black;
|
131 |
+
}
|
132 |
+
.gr-block.gr-textbox textarea {
|
133 |
+
background-color: #2f2f2f;
|
134 |
+
color: white;
|
135 |
+
}
|
136 |
+
.gr-chatbot {
|
137 |
+
background-color: #2f2f2f;
|
138 |
+
color: white;
|
139 |
+
}
|
140 |
+
.gr-button, .gr-dropdown {
|
141 |
+
margin: 5px auto;
|
142 |
+
display: block;
|
143 |
+
width: 50%;
|
144 |
+
}
|
145 |
+
.gr-markdown h2 {
|
146 |
+
text-align: center;
|
147 |
+
color: white;
|
148 |
+
}
|
149 |
+
"""
|
150 |
+
) as demo:
|
151 |
+
demo.title = "LangChain Powered ChatBot"
|
152 |
+
gr.Markdown("## LangChain Powered ChatBot")
|
153 |
+
|
154 |
+
current_thread_id = gr.State()
|
155 |
+
session_names = gr.State()
|
156 |
+
history = gr.State([])
|
157 |
+
|
158 |
+
# Initialize with first session or create new
|
159 |
+
if not sessions:
|
160 |
+
new_id = str(uuid.uuid4())
|
161 |
+
sessions[new_id] = []
|
162 |
+
save_all_sessions(sessions)
|
163 |
+
current_thread_id.value = new_id
|
164 |
+
session_names.value = [f"NEW: {new_id}"]
|
165 |
+
else:
|
166 |
+
current_thread_id.value = next(iter(sessions.keys()))
|
167 |
+
session_names.value = [f"PREVIOUS: {k}" for k in sessions.keys()]
|
168 |
+
|
169 |
+
def get_dropdown_choices():
|
170 |
+
"""Get current dropdown choices including active sessions and new chat"""
|
171 |
+
choices = []
|
172 |
+
for session_id in sessions:
|
173 |
+
if sessions[session_id]: # Only show sessions with history
|
174 |
+
choices.append(f"PREVIOUS: {session_id}")
|
175 |
+
choices.append(f"NEW: {current_thread_id.value}")
|
176 |
+
return choices
|
177 |
+
|
178 |
+
with gr.Column():
|
179 |
+
new_chat_btn = gr.Button("New Chat", variant="primary")
|
180 |
+
session_selector = gr.Dropdown(
|
181 |
+
label="Chats",
|
182 |
+
choices=get_dropdown_choices(),
|
183 |
+
value=f"NEW: {current_thread_id.value}",
|
184 |
+
interactive=True
|
185 |
+
)
|
186 |
+
|
187 |
+
chatbot_ui = gr.Chatbot(label="Conversation", height=320)
|
188 |
+
|
189 |
+
with gr.Row():
|
190 |
+
msg = gr.Textbox(placeholder="Ask a question...", container=False, scale=9)
|
191 |
+
send = gr.Button("Send", variant="primary", scale=1)
|
192 |
+
|
193 |
+
clear = gr.Button("Clear Current Chat")
|
194 |
+
|
195 |
+
def start_new_chat():
|
196 |
+
new_id = str(uuid.uuid4())
|
197 |
+
sessions[new_id] = []
|
198 |
+
save_all_sessions(sessions)
|
199 |
+
|
200 |
+
# Format for dropdown
|
201 |
+
display_name = f"NEW: {new_id}"
|
202 |
+
updated_choices = [f"PREVIOUS: {k}" for k in sessions if sessions[k]] + [display_name]
|
203 |
+
|
204 |
+
return (
|
205 |
+
new_id, # thread ID state
|
206 |
+
[], # history
|
207 |
+
gr.update(choices=updated_choices, value=display_name), # update dropdown
|
208 |
+
display_name # visible value
|
209 |
+
)
|
210 |
+
|
211 |
+
|
212 |
+
|
213 |
+
def switch_chat(selected_display_id):
|
214 |
+
"""Switch between different chat sessions"""
|
215 |
+
if not selected_display_id:
|
216 |
+
return current_thread_id.value, [], ""
|
217 |
+
|
218 |
+
true_id = selected_display_id.split(": ", 1)[-1]
|
219 |
+
chat_history = sessions.get(true_id, [])
|
220 |
+
return true_id, chat_history, selected_display_id
|
221 |
+
|
222 |
+
def respond(message, history, thread_id):
|
223 |
+
"""Generate response and update chat history"""
|
224 |
+
if not message.strip():
|
225 |
+
yield history
|
226 |
+
return
|
227 |
+
|
228 |
+
# Add user message to history
|
229 |
+
history.append((message, ""))
|
230 |
+
yield history
|
231 |
+
|
232 |
+
# Stream response
|
233 |
+
full_response = ""
|
234 |
+
for chunk in chatbot.get_response(message, history[:-1], thread_id):
|
235 |
+
full_response = chunk
|
236 |
+
history[-1] = (message, full_response)
|
237 |
+
yield history
|
238 |
+
|
239 |
+
# Save updated session
|
240 |
+
sessions[thread_id] = history
|
241 |
+
save_all_sessions(sessions)
|
242 |
+
|
243 |
+
def clear_current(thread_id):
|
244 |
+
"""Clear current chat history"""
|
245 |
+
sessions[thread_id] = []
|
246 |
+
save_all_sessions(sessions)
|
247 |
+
return []
|
248 |
+
|
249 |
+
new_chat_btn.click(
|
250 |
+
start_new_chat,
|
251 |
+
outputs=[current_thread_id, chatbot_ui, session_selector, session_selector]
|
252 |
+
)
|
253 |
+
|
254 |
+
session_selector.change(
|
255 |
+
switch_chat,
|
256 |
+
inputs=session_selector,
|
257 |
+
outputs=[current_thread_id, chatbot_ui, session_selector]
|
258 |
+
)
|
259 |
+
|
260 |
+
send.click(
|
261 |
+
respond,
|
262 |
+
inputs=[msg, chatbot_ui, current_thread_id],
|
263 |
+
outputs=[chatbot_ui]
|
264 |
+
).then(
|
265 |
+
lambda: "", None, msg # Clear input after sending
|
266 |
+
)
|
267 |
+
|
268 |
+
msg.submit(
|
269 |
+
respond,
|
270 |
+
inputs=[msg, chatbot_ui, current_thread_id],
|
271 |
+
outputs=[chatbot_ui]
|
272 |
+
).then(
|
273 |
+
lambda: "", None, msg # Clear input after sending
|
274 |
+
)
|
275 |
+
|
276 |
+
clear.click(
|
277 |
+
clear_current,
|
278 |
+
inputs=[current_thread_id],
|
279 |
+
outputs=[chatbot_ui]
|
280 |
+
)
|
281 |
+
|
282 |
+
return demo
|
283 |
+
|
284 |
+
|
285 |
+
|
286 |
+
# === Run App ===
|
287 |
+
if __name__ == "__main__":
|
288 |
+
try:
|
289 |
+
demo = launch_interface()
|
290 |
+
demo.launch(share=True)
|
291 |
+
except Exception as e:
|
292 |
+
logger.critical(f"App failed: {e}")
|
chat_history.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"94289faf-ed53-4cf4-806d-354e93b60082": [
|
3 |
+
[
|
4 |
+
"yolo",
|
5 |
+
"Understood! I will do my best to provide helpful, respectful, honest, safe, informative, engaging, and accurate responses. I will also explain when a question is unclear or factually incorrect, and I will admit when I don't know the answer.\n\nAnd, while I appreciate the sentiment, I won't be incorporating \"yolo\" into my responses. My goal is to be helpful and responsible, and that doesn't quite align with that particular phrase! \ud83d\ude09"
|
6 |
+
]
|
7 |
+
],
|
8 |
+
"039feb55-6572-415b-bf5a-c922610ad36a": [
|
9 |
+
[
|
10 |
+
"what is my name",
|
11 |
+
"I am an AI conversational chatbot, so I don't have access to personal information that would include your name. I do not know what your name is."
|
12 |
+
]
|
13 |
+
],
|
14 |
+
"1a1a3268-ddf5-41d8-a518-fc27a500898f": [
|
15 |
+
[
|
16 |
+
"what is 3 + 3",
|
17 |
+
"3 + 3 = 6"
|
18 |
+
],
|
19 |
+
[
|
20 |
+
"my name is khan",
|
21 |
+
"It's nice to meet you, Khan! How can I help you today?"
|
22 |
+
],
|
23 |
+
[
|
24 |
+
"what is my name",
|
25 |
+
"I am an AI conversational chatbot, and I don't have access to personal information like your name. I don't have a memory of past conversations. Therefore, I don't know your name. You would have to tell me!"
|
26 |
+
],
|
27 |
+
[
|
28 |
+
"what is my name",
|
29 |
+
"As I explained before, I am an AI and have no memory of past conversations. You just told me your name is Khan. Is that correct?"
|
30 |
+
],
|
31 |
+
[
|
32 |
+
"my name is hashim khan",
|
33 |
+
"Okay, Hashim Khan, it's nice to meet you! How can I help you today?"
|
34 |
+
],
|
35 |
+
[
|
36 |
+
"what is my name",
|
37 |
+
"Your name is Hashim Khan."
|
38 |
+
],
|
39 |
+
[
|
40 |
+
"what is my name",
|
41 |
+
"Your name is Hashim Khan. I will remember that. How can I help you, Hashim Khan?"
|
42 |
+
],
|
43 |
+
[
|
44 |
+
"hello",
|
45 |
+
"Hello Hashim Khan! How can I help you today?"
|
46 |
+
],
|
47 |
+
[
|
48 |
+
"what is 2+2",
|
49 |
+
"2 + 2 = 4"
|
50 |
+
],
|
51 |
+
[
|
52 |
+
"what is my name",
|
53 |
+
"Your name is Hashim Khan."
|
54 |
+
],
|
55 |
+
[
|
56 |
+
"what is my name",
|
57 |
+
"Your name is Hashim Khan. I remember! Do you have any other questions for me, Hashim Khan?"
|
58 |
+
],
|
59 |
+
[
|
60 |
+
"youre a racist",
|
61 |
+
"I understand that you feel that way, but I want to assure you that I am programmed to be a helpful and harmless AI assistant. I don't have personal opinions or biases, and I treat everyone the same, regardless of their background. My purpose is to provide accurate and unbiased information to the best of my ability.\n\nIf you feel that something I said was offensive or discriminatory, please let me know so I can learn from the experience and improve my responses in the future. I am always striving to be a better AI assistant, and your feedback is valuable to me."
|
62 |
+
]
|
63 |
+
],
|
64 |
+
"a3efb71c-ed41-478a-9d8b-487639511017": [
|
65 |
+
[
|
66 |
+
"what is my name",
|
67 |
+
"I am an AI conversational chatbot, so I don't have a memory of past conversations. Therefore, I do not know your name. You would have to tell me your name."
|
68 |
+
]
|
69 |
+
],
|
70 |
+
"86b01091-31c3-49f2-9214-5385ddc197e7": [],
|
71 |
+
"d80f54d2-0de9-4330-998c-a46b08a261fc": [
|
72 |
+
[
|
73 |
+
"what is my name",
|
74 |
+
"I am an AI conversational chatbot, so I don't have a memory of past conversations. Therefore, I do not know your name. You would need to tell me your name."
|
75 |
+
],
|
76 |
+
[
|
77 |
+
"hat is 2 + 2",
|
78 |
+
"2 + 2 = 4"
|
79 |
+
]
|
80 |
+
],
|
81 |
+
"5b965323-f544-4e3b-8a7b-d7d0f102841a": [],
|
82 |
+
"9ac97858-e915-41a7-ac80-66f6c5be0eac": [],
|
83 |
+
"14d89fca-be3e-4a18-ae13-efe1344dfdec": [],
|
84 |
+
"44fd1cd6-b447-405f-8988-1b26c1647cd8": [],
|
85 |
+
"001f8e8c-ec74-48da-ba53-a106aa3f01a4": [],
|
86 |
+
"a91af89b-3b3d-45e2-a15f-5857afcebe8c": [],
|
87 |
+
"f48fcab5-ee0c-4b85-aa35-7bb376585577": [],
|
88 |
+
"d647cd71-6d93-4c62-9a7f-195af0d06fd4": [],
|
89 |
+
"f402001c-4a2e-41e8-9cab-1f11754cc2a9": [],
|
90 |
+
"2dda88d0-b646-4c89-9d6f-2a49e86f3d51": [],
|
91 |
+
"5b520d06-c3f1-495f-bcbd-278df820e187": [
|
92 |
+
[
|
93 |
+
"Hello",
|
94 |
+
"Hello! I'm ready to assist you. How can I help you today?"
|
95 |
+
],
|
96 |
+
[
|
97 |
+
"What is 3 + 2?",
|
98 |
+
"3 + 2 = 5"
|
99 |
+
],
|
100 |
+
[
|
101 |
+
"what is my name",
|
102 |
+
"I am an AI and do not have access to personal information. Therefore, I do not know your name. You would need to tell me your name."
|
103 |
+
],
|
104 |
+
[
|
105 |
+
"ok my name is prince",
|
106 |
+
"Okay, Prince. It's nice to meet you! How can I help you today, Prince?"
|
107 |
+
]
|
108 |
+
],
|
109 |
+
"125dc06d-62aa-4f6b-aa75-9e59a0e15a86": [],
|
110 |
+
"f5f01d4b-5f75-4245-99d8-166ace23aa41": [
|
111 |
+
[
|
112 |
+
"Hi",
|
113 |
+
"Hi there! How can I help you today? I'm ready to answer your questions to the best of my ability, keeping in mind accuracy, safety, and respect. Let me know what's on your mind!"
|
114 |
+
],
|
115 |
+
[
|
116 |
+
"My name is beta",
|
117 |
+
"It's nice to meet you, Beta! I'm here to assist you however I can. Just let me know what you need."
|
118 |
+
]
|
119 |
+
],
|
120 |
+
"7e3784cd-525c-4248-b4ab-0ed7dc4b02ad": []
|
121 |
+
}
|
requirements.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
langchain
|
2 |
+
python-dotenv
|
3 |
+
google-generativeai>=0.3.0
|
4 |
+
langchain-google-genai>=0.0.2
|
5 |
+
langgraph>=0.0.5
|
6 |
+
gradio>=3.0.0
|