Chong-U Lim commited on
Commit
7077707
·
1 Parent(s): 4169230

Update readme

Browse files
Files changed (2) hide show
  1. README.md +9 -8
  2. notebook.ipynb +52 -14
README.md CHANGED
@@ -14,18 +14,19 @@ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-
14
 
15
  ```
16
 
17
- # In (base)
18
- conda install -c conda-forge notebook
19
- conda install -c conda-forge nb_conda_kernels
20
 
21
- conda create -n "codebasics-langchain-crash-course" python=3.10
22
- conda use codebasics-langchain-crash-course
 
 
 
 
23
 
24
- # In (codebasics-langchain-crash-course)
25
 
26
  # Acknowledgements
27
  The code is based on original tutorial series by [@codebasics](https://twitter.com/codebasicshub).
28
- * [LangChain Crash Course For Beginners](https://www.youtube.com/watch?v=nAmC7SoVLd8&list=PLeo1K3hjS3uu0N_0W6giDXzZIcB07Ng_F&ab_channel=codebasics)
29
-
30
 
31
  ```
 
14
 
15
  ```
16
 
17
+ # Introduction
18
+ This repository contains the code for generating a restaurant name and menu items based on an input cuisine.
19
+ It makes use of [LangChain](http://www.langchain.com) and OpenAI's chatGPT API, along with [Gradio](http://gradio.app) to serve an application.
20
 
21
+ The original [LangChain Crash Course For Beginners tutorial](https://www.youtube.com/watch?v=nAmC7SoVLd8&list=PLeo1K3hjS3uu0N_0W6giDXzZIcB07Ng_F&ab_channel=codebasics) by [@codebasics](https://twitter.com/codebasicshub) used an older version of LangChain and Streamlit for the app.
22
+
23
+ The code here uses updated libraries and Gradio in place of Streamlit.
24
+
25
+ # Demo
26
+ You can play around with the demo app on [this Hugging Face Space](https://huggingface.co/spaces/chongdashu/langchain-crash-course-gradio)
27
 
 
28
 
29
  # Acknowledgements
30
  The code is based on original tutorial series by [@codebasics](https://twitter.com/codebasicshub).
 
 
31
 
32
  ```
notebook.ipynb CHANGED
@@ -6,8 +6,8 @@
6
  "metadata": {},
7
  "outputs": [],
8
  "source": [
9
- "# !pip install -q langchain\n",
10
- "# !pip install -q openai"
11
  ]
12
  },
13
  {
@@ -192,26 +192,18 @@
192
  },
193
  {
194
  "cell_type": "code",
195
- "execution_count": 12,
196
  "metadata": {},
197
  "outputs": [
198
- {
199
- "name": "stderr",
200
- "output_type": "stream",
201
- "text": [
202
- "/home/chong-u/mambaforge/envs/codebasics-langchain-crash-course/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `__call__` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
203
- " warn_deprecated(\n"
204
- ]
205
- },
206
  {
207
  "data": {
208
  "text/plain": [
209
  "{'cuisine': 'Singaporean',\n",
210
- " 'restaurant_name': '\\n\\n\"Singapore Spice Emporium\"',\n",
211
- " 'menu_items': '\\n\\n\"Nasi Lemak, Hainanese Chicken Rice, Laksa, Chili Crab, Char Kway Teow, Satay, Rojak, Bak Kut Teh, Curry Puffs, Teh Tarik\"'}"
212
  ]
213
  },
214
- "execution_count": 12,
215
  "metadata": {},
216
  "output_type": "execute_result"
217
  }
@@ -228,6 +220,52 @@
228
  "chain.invoke({\"cuisine\": \"Singaporean\"})"
229
  ]
230
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
231
  {
232
  "cell_type": "code",
233
  "execution_count": null,
 
6
  "metadata": {},
7
  "outputs": [],
8
  "source": [
9
+ "# !pip install -q langchain==0.1.9\n",
10
+ "# !pip install -q openai==1.13.3"
11
  ]
12
  },
13
  {
 
192
  },
193
  {
194
  "cell_type": "code",
195
+ "execution_count": 13,
196
  "metadata": {},
197
  "outputs": [
 
 
 
 
 
 
 
 
198
  {
199
  "data": {
200
  "text/plain": [
201
  "{'cuisine': 'Singaporean',\n",
202
+ " 'restaurant_name': '\\n\"Straits Flavors\"',\n",
203
+ " 'menu_items': '\\n\\nSambal Shrimp, Roti Canai, Nasi Lemak, Beef Rendang, Satay Skewers, Hainanese Chicken Rice, Char Kway Teow, Laksa Soup, Rojak Salad, Curry Puffs'}"
204
  ]
205
  },
206
+ "execution_count": 13,
207
  "metadata": {},
208
  "output_type": "execute_result"
209
  }
 
220
  "chain.invoke({\"cuisine\": \"Singaporean\"})"
221
  ]
222
  },
223
+ {
224
+ "cell_type": "markdown",
225
+ "metadata": {},
226
+ "source": [
227
+ "## Agents"
228
+ ]
229
+ },
230
+ {
231
+ "cell_type": "code",
232
+ "execution_count": 20,
233
+ "metadata": {},
234
+ "outputs": [],
235
+ "source": [
236
+ "!pip install -q wikipedia\n",
237
+ "!pip install -q numexpr # for llm-math"
238
+ ]
239
+ },
240
+ {
241
+ "cell_type": "code",
242
+ "execution_count": 21,
243
+ "metadata": {
244
+ "notebookRunGroups": {
245
+ "groupValue": "1"
246
+ }
247
+ },
248
+ "outputs": [],
249
+ "source": [
250
+ "from langchain.agents import AgentType, initialize_agent, load_tools\n",
251
+ "from langchain.llms import OpenAI"
252
+ ]
253
+ },
254
+ {
255
+ "cell_type": "code",
256
+ "execution_count": 22,
257
+ "metadata": {},
258
+ "outputs": [],
259
+ "source": [
260
+ "tools = load_tools([\"wikipedia\", \"llm-math\"], llm=llm)\n",
261
+ "\n",
262
+ "initialize_agent(\n",
263
+ " tools,\n",
264
+ " llm,\n",
265
+ " agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
266
+ ")"
267
+ ]
268
+ },
269
  {
270
  "cell_type": "code",
271
  "execution_count": null,