Add pip install command to example notebook - (#12253)

e91c81dc · milind · GitHub · eb90f252 · e91c81dc
Unverified Commit e91c81dc authored 11 months ago by milind Committed by GitHub 11 months ago
--- a/llama-index-integrations/tools/llama-index-tools-code-interpreter/examples/code_interpreter.ipynb
+++ b/llama-index-integrations/tools/llama-index-tools-code-interpreter/examples/code_interpreter.ipynb
 {
 "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "81491dcf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index-agent-openai\n",
+    "%pip install llama-index-llms-openai\n",
+    "%pip install llama-index-tools-code-interpreter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "808c3a29",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-index"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": null,

+%% Cell type:code id:81491dcf tags:
+``` python
+%pip install llama-index-agent-openai
+%pip install llama-index-llms-openai
+%pip install llama-index-tools-code-interpreter
+```
+%% Cell type:code id:808c3a29 tags:
+``` python
+!pip install llama-index
+```
 %% Cell type:code id:5bd51289-b88e-4ed2-b652-3ad9949e62f6 tags:
 ``` python
 import openai
 openai.api_key = "sk-key"
 ```
 %% Cell type:code id:f0de43a8-bc30-4f00-99dd-e94a2c4f2452 tags:
 ``` python
 from llama_index.agent import OpenAIAgent
 ```
 %% Cell type:code id:7744f90f-ea51-42da-b8fb-f57e5e8ed410 tags:
 ``` python
 # Import and initialize our tool spec
 from llama_index.tools.code_interpreter.base import CodeInterpreterToolSpec
 code_spec = CodeInterpreterToolSpec()
 tools = code_spec.to_tool_list()
 # Create the Agent with our tools
 agent = OpenAIAgent.from_tools(tools, verbose=True)
 ```
 %% Cell type:code id:c048da6f-1a04-444a-8028-ab0d80b7a232 tags:
 ``` python
 # Prime the Agent to use the tool
 print(
    agent.chat(
        "Can you help me write some python code to pass to the code_interpreter tool"
    )
 )
 ```
 %% Output
    Of course! I'd be happy to help you write some Python code. What specific task or problem would you like the code to solve?
 %% Cell type:code id:ea736eb8-1a40-43d1-ac40-332f2b74689a tags:
 ``` python
 print(
    agent.chat(
        """There is a world_happiness_2016.csv file in the `data` directory (relative path).
                 Can you write and execute code to tell me columns does it have?"""
    )
 )
 ```
 %% Output
    === Calling Function ===
    Calling function: code_interpreter with args: {
      "code": "import pandas as pd\n\n# Read the CSV file\ndata = pd.read_csv('data/world_happiness_2016.csv')\n\n# Get the column names\ncolumns = data.columns.tolist()\n\n# Print the column names\nprint(columns)"
    }
    Got output: StdOut:
    b"['Country', 'Region', 'Happiness Rank', 'Happiness Score', 'Lower Confidence Interval', 'Upper Confidence Interval', 'Economy (GDP per Capita)', 'Family', 'Health (Life Expectancy)', 'Freedom', 'Trust (Government Corruption)', 'Generosity', 'Dystopia Residual']\n"
    StdErr:
    b''
    ========================
    The `world_happiness_2016.csv` file has the following columns:
    - Country
    - Region
    - Happiness Rank
    - Happiness Score
    - Lower Confidence Interval
    - Upper Confidence Interval
    - Economy (GDP per Capita)
    - Family
    - Health (Life Expectancy)
    - Freedom
    - Trust (Government Corruption)
    - Generosity
    - Dystopia Residual
    Let me know if there's anything else I can help you with!
 %% Cell type:code id:b7aad761-51ff-4948-94c8-011eed201b78 tags:
 ``` python
 print(agent.chat("What are the top 10 happiest countries"))
 ```
 %% Output
    === Calling Function ===
    Calling function: code_interpreter with args: {
      "code": "import pandas as pd\n\n# Read the CSV file\ndata = pd.read_csv('data/world_happiness_2016.csv')\n\n# Sort the data by Happiness Score in descending order\ndata_sorted = data.sort_values('Happiness Score', ascending=False)\n\n# Get the top 10 happiest countries\ntop_10_happiest = data_sorted.head(10)\n\n# Print the top 10 happiest countries\nprint(top_10_happiest[['Country', 'Happiness Score']])"
    }
    Got output: StdOut:
    b'       Country  Happiness Score\n0      Denmark            7.526\n1  Switzerland            7.509\n2      Iceland            7.501\n3       Norway            7.498\n4      Finland            7.413\n5       Canada            7.404\n6  Netherlands            7.339\n7  New Zealand            7.334\n8    Australia            7.313\n9       Sweden            7.291\n'
    StdErr:
    b''
    ========================
    The top 10 happiest countries according to the `world_happiness_2016.csv` file are:
    1. Denmark - Happiness Score: 7.526
    2. Switzerland - Happiness Score: 7.509
    3. Iceland - Happiness Score: 7.501
    4. Norway - Happiness Score: 7.498
    5. Finland - Happiness Score: 7.413
    6. Canada - Happiness Score: 7.404
    7. Netherlands - Happiness Score: 7.339
    8. New Zealand - Happiness Score: 7.334
    9. Australia - Happiness Score: 7.313
    10. Sweden - Happiness Score: 7.291
    Let me know if there's anything else I can assist you with!
 %% Cell type:code id:4ba99822-42d1-4599-b5d1-6e03362b87eb tags:
 ``` python
 print(agent.chat("Can you make a graph of the top 10 happiest countries"))
 ```
 %% Output
    === Calling Function ===
    Calling function: code_interpreter with args: {
      "code": "import pandas as pd\nimport matplotlib.pyplot as plt\n\n# Read the CSV file\ndata = pd.read_csv('data/world_happiness_2016.csv')\n\n# Sort the data by Happiness Score in descending order\ndata_sorted = data.sort_values('Happiness Score', ascending=False)\n\n# Get the top 10 happiest countries\ntop_10_happiest = data_sorted.head(10)\n\n# Create a bar plot of the Happiness Score for the top 10 happiest countries\nplt.figure(figsize=(10, 6))\nplt.bar(top_10_happiest['Country'], top_10_happiest['Happiness Score'])\nplt.xlabel('Country')\nplt.ylabel('Happiness Score')\nplt.title('Top 10 Happiest Countries')\nplt.xticks(rotation=45)\nplt.show()"
    }
    Got output: StdOut:
    b'Figure(1000x600)\n'
    StdErr:
    b''
    ========================
    Here is a bar plot showing the Happiness Score for the top 10 happiest countries:
    ![Top 10 Happiest Countries](output.png)
    Let me know if there's anything else I can help you with!
 %% Cell type:code id:cfe26afe-f86d-4ec3-8197-63f8446df43a tags:
 ``` python
 print(
    agent.chat(
        "I cant see the plot - can you save it locally with file name `output.png`?"
    )
 )
 ```
 %% Output
    === Calling Function ===
    Calling function: code_interpreter with args: {
      "code": "import pandas as pd\nimport matplotlib.pyplot as plt\n\n# Read the CSV file\ndata = pd.read_csv('data/world_happiness_2016.csv')\n\n# Sort the data by Happiness Score in descending order\ndata_sorted = data.sort_values('Happiness Score', ascending=False)\n\n# Get the top 10 happiest countries\ntop_10_happiest = data_sorted.head(10)\n\n# Create a bar plot of the Happiness Score for the top 10 happiest countries\nplt.figure(figsize=(10, 6))\nplt.bar(top_10_happiest['Country'], top_10_happiest['Happiness Score'])\nplt.xlabel('Country')\nplt.ylabel('Happiness Score')\nplt.title('Top 10 Happiest Countries')\nplt.xticks(rotation=45)\nplt.savefig('output.png')\nplt.close()"
    }
    Got output: StdOut:
    b''
    StdErr:
    b''
    ========================
    I have saved the bar plot as `output.png` in the current directory. You can download it using the following link:
    [Download output.png](sandbox:/output.png)
    Let me know if there's anything else I can assist you with!
 %% Cell type:code id:a6d48d83-4556-456d-ba7e-34406124c58b tags:
 ``` python
 print(agent.chat("can you also plot the 10 lowest"))
 ```
 %% Output
    === Calling Function ===
    Calling function: code_interpreter with args: {
      "code": "import pandas as pd\nimport matplotlib.pyplot as plt\n\n# Read the CSV file\ndata = pd.read_csv('data/world_happiness_2016.csv')\n\n# Sort the data by Happiness Score in ascending order\ndata_sorted = data.sort_values('Happiness Score', ascending=True)\n\n# Get the 10 lowest happiest countries\ntop_10_lowest = data_sorted.head(10)\n\n# Create a bar plot of the Happiness Score for the 10 lowest happiest countries\nplt.figure(figsize=(10, 6))\nplt.bar(top_10_lowest['Country'], top_10_lowest['Happiness Score'])\nplt.xlabel('Country')\nplt.ylabel('Happiness Score')\nplt.title('10 Lowest Happiest Countries')\nplt.xticks(rotation=45)\nplt.savefig('lowest_output.png')\nplt.close()"
    }
    Got output: StdOut:
    b''
    StdErr:
    b''
    ========================
    I have saved the bar plot of the 10 lowest happiest countries as `lowest_output.png` in the current directory. You can download it using the following link:
    [Download lowest_output.png](sandbox:/lowest_output.png)
    Let me know if there's anything else I can assist you with!
 %% Cell type:code id:91ad753b-6c41-4c85-b59d-ff9b57507cc5 tags:
 ``` python
 agent.chat("can you do it in one plot")
 ```
 %% Output
    === Calling Function ===
    Calling function: code_interpreter with args: {
      "code": "import pandas as pd\nimport matplotlib.pyplot as plt\n\n# Read the CSV file\ndata = pd.read_csv('data/world_happiness_2016.csv')\n\n# Sort the data by Happiness Score in ascending order\ndata_sorted = data.sort_values('Happiness Score', ascending=True)\n\n# Get the 10 lowest happiest countries\ntop_10_lowest = data_sorted.head(10)\n\n# Sort the data by Happiness Score in descending order\ndata_sorted = data.sort_values('Happiness Score', ascending=False)\n\n# Get the top 10 happiest countries\ntop_10_happiest = data_sorted.head(10)\n\n# Create a bar plot of the Happiness Score for the top 10 happiest and 10 lowest happiest countries\nplt.figure(figsize=(12, 6))\nplt.bar(top_10_happiest['Country'], top_10_happiest['Happiness Score'], label='Top 10 Happiest')\nplt.bar(top_10_lowest['Country'], top_10_lowest['Happiness Score'], label='10 Lowest Happiest')\nplt.xlabel('Country')\nplt.ylabel('Happiness Score')\nplt.title('Happiness Score Comparison')\nplt.xticks(rotation=45)\nplt.legend()\nplt.savefig('happiness_comparison.png')\nplt.close()"
    }
    Got output: StdOut:
    b''
    StdErr:
    b''
    ========================
    AgentChatResponse(response="I have created a bar plot comparing the Happiness Score of the top 10 happiest countries and the 10 lowest happiest countries. The plot is saved as `happiness_comparison.png` in the current directory. You can download it using the following link:\n\n[Download happiness_comparison.png](sandbox:/happiness_comparison.png)\n\nLet me know if there's anything else I can assist you with!", sources=[ToolOutput(content="StdOut:\nb''\nStdErr:\nb''", tool_name='code_interpreter', raw_input={'args': (), 'kwargs': {'code': "import pandas as pd\nimport matplotlib.pyplot as plt\n\n# Read the CSV file\ndata = pd.read_csv('data/world_happiness_2016.csv')\n\n# Sort the data by Happiness Score in ascending order\ndata_sorted = data.sort_values('Happiness Score', ascending=True)\n\n# Get the 10 lowest happiest countries\ntop_10_lowest = data_sorted.head(10)\n\n# Sort the data by Happiness Score in descending order\ndata_sorted = data.sort_values('Happiness Score', ascending=False)\n\n# Get the top 10 happiest countries\ntop_10_happiest = data_sorted.head(10)\n\n# Create a bar plot of the Happiness Score for the top 10 happiest and 10 lowest happiest countries\nplt.figure(figsize=(12, 6))\nplt.bar(top_10_happiest['Country'], top_10_happiest['Happiness Score'], label='Top 10 Happiest')\nplt.bar(top_10_lowest['Country'], top_10_lowest['Happiness Score'], label='10 Lowest Happiest')\nplt.xlabel('Country')\nplt.ylabel('Happiness Score')\nplt.title('Happiness Score Comparison')\nplt.xticks(rotation=45)\nplt.legend()\nplt.savefig('happiness_comparison.png')\nplt.close()"}}, raw_output="StdOut:\nb''\nStdErr:\nb''")])