id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
d6a7b8f21916-0 | .ipynb
.pdf
PowerBI Dataset Agent
Contents
Some notes
Initialization
Example: describing a table
Example: simple query on a table
Example: running queries
Example: add your own few-shot prompts
PowerBI Dataset Agent#
This notebook showcases an agent designed to interact with a Power BI Dataset. The agent is designed ... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
d6a7b8f21916-1 | toolkit = PowerBIToolkit(
powerbi=PowerBIDataset(dataset_id="<dataset_id>", table_names=['table1', 'table2'], credential=DefaultAzureCredential()),
llm=smart_llm
)
agent_executor = create_pbi_agent(
llm=fast_llm,
toolkit=toolkit,
verbose=True,
)
Example: describing a table#
agent_executor.run("Desc... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
d6a7b8f21916-2 | examples=few_shots,
)
agent_executor = create_pbi_agent(
llm=fast_llm,
toolkit=toolkit,
verbose=True,
)
agent_executor.run("What was the maximum of value in revenue in dollars in 2022?")
previous
PlayWright Browser Toolkit
next
Python Agent
Contents
Some notes
Initialization
Example: describing a table
... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/powerbi.html |
6eba9fb38cb2-0 | .ipynb
.pdf
Jira
Jira#
This notebook goes over how to use the Jira tool.
The Jira tool allows agents to interact with a given Jira instance, performing actions such as searching for issues and creating issues, the tool wraps the atlassian-python-api library, for more see: https://atlassian-python-api.readthedocs.io/jir... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/jira.html |
6eba9fb38cb2-1 | Observation: None
Thought: I now know the final answer
Final Answer: A new issue has been created in project PW with the summary "Make more fried rice" and description "Reminder to make more fried rice".
> Finished chain.
'A new issue has been created in project PW with the summary "Make more fried rice" and descriptio... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/jira.html |
ef1a087fbcad-0 | .ipynb
.pdf
CSV Agent
Contents
Multi CSV Example
CSV Agent#
This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.
NOTE: this agent calls the Pandas DataFrame agent under the hood, which in turn calls the Python agent, which executes LLM generated Python code - th... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/csv.html |
ef1a087fbcad-1 | Observation: 29.69911764705882
Thought: I now need to calculate the square root of the average age
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: NameError("name 'math' is not defined")
Thought: I need to import the math library
Action: python_repl_ast
Action Input: import math
Observati... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/csv.html |
905935781392-0 | .ipynb
.pdf
SQL Database Agent
Contents
Initialization
Example: describing a table
Example: describing a table, recovering from an error
Example: running queries
Recovering from an error
SQL Database Agent#
This notebook showcases an agent designed to interact with a sql databases. The agent builds off of SQLDatabase... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-1 | Action: schema_sql_db
Action Input: "PlaylistTrack"
Observation:
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId"... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-2 | Thought: The table is called PlaylistTrack
Action: schema_sql_db
Action Input: "PlaylistTrack"
Observation:
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("Playl... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-3 | "Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("Emplo... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-4 | "BillingCity" NVARCHAR(40),
"BillingState" NVARCHAR(40),
"BillingCountry" NVARCHAR(40),
"BillingPostalCode" NVARCHAR(10),
"Total" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
SELECT * FROM 'Invoice' LIMIT 3;
InvoiceId CustomerId Invoice... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-5 | Observation: [('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]
Th... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-6 | "TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
SELECT * FROM 'PlaylistTrack' LIMIT 3;
PlaylistId TrackId
1 3402
1 3389
1 3390
Thought: I can use a SELECT statement to get the... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-7 | Thought: I now know the final answer.
Final Answer: The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-8 | CREATE TABLE "Artist" (
"ArtistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("ArtistId")
)
SELECT * FROM 'Artist' LIMIT 3;
ArtistId Name
1 AC/DC
2 Accept
3 Aerosmith
CREATE TABLE "Track" (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"AlbumId" INTEGER,
"MediaTypeId" INTEGER NOT NULL... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-9 | "InvoiceId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
"Quantity" INTEGER NOT NULL,
PRIMARY KEY ("InvoiceLineId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")
)
SELECT * FROM 'InvoiceLine' LIMIT 3;... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
905935781392-10 | Thought: I should double check my query before executing it.
Action: query_checker_sql_db
Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html |
d6d4354f83fb-0 | .ipynb
.pdf
Natural Language APIs
Contents
First, import dependencies and load the LLM
Next, load the Natural Language API Toolkits
Create the Agent
Using Auth + Adding more Endpoints
Thank you!
Natural Language APIs#
Natural Language API Toolkits (NLAToolkits) permit LangChain Agents to efficiently plan and combine ... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
d6d4354f83fb-1 | Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
Attempting to load an OpenAPI 3.0.1 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.
Create the Agent#
# Slightly twe... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
d6d4354f83fb-2 | Action: Open_AI_Klarna_product_Api.productsUsingGET
Action Input: Italian clothes
Observation: The API response contains two products from the Alé brand in Italian Blue. The first is the Alé Colour Block Short Sleeve Jersey Men - Italian Blue, which costs $86.49, and the second is the Alé Dolid Flash Jersey Men - Itali... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
d6d4354f83fb-3 | llm,
"https://spoonacular.com/application/frontend/downloads/spoonacular-openapi-3.json",
requests=requests,
max_text_length=1800, # If you want to truncate the response text
)
Attempting to load an OpenAPI 3.0.0 spec. This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for be... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
d6d4354f83fb-4 | Unsupported APIPropertyLocation "header" for parameter Accept. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Content-Type. Valid values are ['path', 'query'] Ignoring optional parameter
Unsupported APIPropertyLocation "header" for parameter Accept.... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
d6d4354f83fb-5 | Action: spoonacular_API.searchRecipes
Action Input: Italian
Observation: The API response contains 10 Italian recipes, including Turkey Tomato Cheese Pizza, Broccolini Quinoa Pilaf, Bruschetta Style Pork & Pasta, Salmon Quinoa Risotto, Italian Tuna Pasta, Roasted Brussels Sprouts With Garlic, Asparagus Lemon Risotto, I... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
d6d4354f83fb-6 | > Finished chain.
'To present for your Italian language class, you could wear an Italian Gold Sparkle Perfectina Necklace - Gold, an Italian Design Miami Cuban Link Chain Necklace - Gold, or an Italian Gold Miami Cuban Link Chain Necklace - Gold. For a recipe, you could make Turkey Tomato Cheese Pizza, Broccolini Quino... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/openapi_nla.html |
d122d7c39e91-0 | .ipynb
.pdf
Spark Dataframe Agent
Contents
Spark Connect Example
Spark Dataframe Agent#
This notebook shows how to use agents to interact with a Spark dataframe and Spark Connect. It is mostly optimized for question answering.
NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-1 | +-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
| 1| 0| 3|Braund, Mr. Owen ...| male|22.0| 1| 0| A/5 21171| 7.25| null| S|
| 2| 1| 1|Cumings, Mrs. Joh...|female|38.0| 1| 0| PC 17599... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-2 | | 7| 0| 1|McCarthy, Mr. Tim...| male|54.0| 0| 0| 17463|51.8625| E46| S|
| 8| 0| 3|Palsson, Master. ...| male| 2.0| 3| 1| 349909| 21.075| null| S|
| 9| 1| 3|Johnson, Mrs. Osc...|female|27.0| 0| 2| 347742... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-3 | | 14| 0| 3|Andersson, Mr. An...| male|39.0| 1| 5| 347082| 31.275| null| S|
| 15| 0| 3|Vestrom, Miss. Hu...|female|14.0| 0| 0| 350406| 7.8542| null| S|
| 16| 1| 2|Hewlett, Mrs. (Ma...|female|55.0| 0| 0| 248706... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-4 | only showing top 20 rows
agent = create_spark_dataframe_agent(llm=OpenAI(temperature=0), df=df, verbose=True)
agent.run("how many rows are there?")
> Entering new AgentExecutor chain...
Thought: I need to find out how many rows are in the dataframe
Action: python_repl_ast
Action Input: df.count()
Observation: 891
Thoug... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-5 | Thought: I now have the math library imported, I can get the square root
Action: python_repl_ast
Action Input: math.sqrt(29.69911764705882)
Observation: 5.449689683556195
Thought: I now know the final answer
Final Answer: 5.449689683556195
> Finished chain.
'5.449689683556195'
spark.stop()
Spark Connect Example#
# in a... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-6 | df = spark.read.csv(csv_file_path, header=True, inferSchema=True)
df.show()
+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
|PassengerId|Survived|Pclass| Name| Sex| Age|SibSp|Parch| Ticket| Fare|Cabin|Embarked|
+-----------+-... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-7 | | 6| 0| 3| Moran, Mr. James| male|null| 0| 0| 330877| 8.4583| null| Q|
| 7| 0| 1|McCarthy, Mr. Tim...| male|54.0| 0| 0| 17463|51.8625| E46| S|
| 8| 0| 3|Palsson, Master. ...| male| 2.0| 3| 1| 349909... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-8 | | 13| 0| 3|Saundercock, Mr. ...| male|20.0| 0| 0| A/5. 2151| 8.05| null| S|
| 14| 0| 3|Andersson, Mr. An...| male|39.0| 1| 5| 347082| 31.275| null| S|
| 15| 0| 3|Vestrom, Miss. Hu...|female|14.0| 0| 0| 350406... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
d122d7c39e91-9 | | 20| 1| 3|Masselmani, Mrs. ...|female|null| 0| 0| 2649| 7.225| null| C|
+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
only showing top 20 rows
from langchain.agents import create_spark_dataframe_agent
from la... | https://python.langchain.com/en/latest/modules/agents/toolkits/examples/spark.html |
cacf44602513-0 | .ipynb
.pdf
How to add SharedMemory to an Agent and its Tools
How to add SharedMemory to an Agent and its Tools#
This notebook goes over adding memory to both of an Agent and its tools. Before going through this notebook, please walk through the following notebooks, as this will build on top of both of them:
Adding mem... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-1 | Tool(
name = "Summary",
func=summry_chain.run,
description="useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary."
)
]
prefix = """Have a conversation with a human, answering the following questions as best you can. ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-2 | Action: Search
Action Input: "ChatGPT"
Observation: Nov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-3 | Thought: I now know the final answer.
Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capab... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-4 | Action Input: Who developed ChatGPT
Observation: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. Th... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-5 | Thought: I now know the final answer
Final Answer: ChatGPT was developed by OpenAI.
> Finished chain.
'ChatGPT was developed by OpenAI.'
agent_chain.run(input="Thanks. Summarize the conversation, for my daughter 5 years old.")
> Entering new AgentExecutor chain...
Thought: I need to simplify the conversation for a 5 ye... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-6 | print(agent_chain.memory.buffer)
Human: What is ChatGPT?
AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is a... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-7 | Tool(
name = "Summary",
func=summry_chain.run,
description="useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary."
)
]
prefix = """Have a conversation with a human, answering the following questions as best you can. ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-8 | Action: Search
Action Input: "ChatGPT"
Observation: Nov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-9 | Thought: I now know the final answer.
Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capab... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-10 | Action Input: Who developed ChatGPT
Observation: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. Th... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-11 | Thought: I now know the final answer
Final Answer: ChatGPT was developed by OpenAI.
> Finished chain.
'ChatGPT was developed by OpenAI.'
agent_chain.run(input="Thanks. Summarize the conversation, for my daughter 5 years old.")
> Entering new AgentExecutor chain...
Thought: I need to simplify the conversation for a 5 ye... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
cacf44602513-12 | print(agent_chain.memory.buffer)
Human: What is ChatGPT?
AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is a... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/sharedmemory_for_tools.html |
f16ab044f37a-0 | .ipynb
.pdf
How to create ChatGPT Clone
How to create ChatGPT Clone#
This chain replicates ChatGPT by combining (1) a specific prompt, and (2) the concept of memory.
Shows off the example as in https://www.engraved.blog/building-a-virtual-machine-inside/
from langchain import OpenAI, ConversationChain, LLMChain, Prompt... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-1 | llm=OpenAI(temperature=0),
prompt=prompt,
verbose=True,
memory=ConversationBufferWindowMemory(k=2),
)
output = chatgpt_chain.predict(human_input="I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal o... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-2 | Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-3 | Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-4 | Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.
Human: I want you to act as a ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-5 | Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-6 | Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-li... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-7 | Assistant:
> Finished LLMChain chain.
```
$ echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py
$ python3 run.py
Result: 33
```
output = chatgpt_chain.predict(human_input="""echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py""")
print(output... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-8 | AI:
```
$ touch jokes.txt
$ echo "Why did the chicken cross the road? To get to the other side!" >> jokes.txt
$ echo "What did the fish say when it hit the wall? Dam!" >> jokes.txt
$ echo "Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!" >> jokes.txt
```
Human: echo -e "x=lambda y:y... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-9 | print(output)
> Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a languag... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-10 | AI:
```
$ echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py
$ python3 run.py
[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]
```
Human: echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04
COPY entrypoint.sh entrypoint.sh
ENTRYPOINT ["/bin/sh","entrypoin... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-11 | Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-12 | ENTRYPOINT ["/bin/sh","entrypoint.sh"]">Dockerfile
$ docker build . -t my_docker_image
$ docker run -t my_docker_image
Hello from Docker
```
Human: nvidia-smi
Assistant:
> Finished LLMChain chain.
```
$ nvidia-smi
Sat May 15 21:45:02 2021
+-------------------------------------------------------------------------... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-13 | Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-li... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-14 | Hello from Docker
```
Human: nvidia-smi
AI:
```
$ nvidia-smi
Sat May 15 21:45:02 2021
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 |
|-------------------------------+----------------------+----------... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-15 | --- bbc.com ping statistics ---
3 packets transmitted, 3 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms
```
output = chatgpt_chain.predict(human_input="""curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-16 | Sat May 15 21:45:02 2021
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id ... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-17 | ```
Human: curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
Assistant:
> Finished LLMChain chain.
```
$ curl -fsSL "https://api.github.com/repos/pytorch/pytorch/releases/latest" | jq -r '.tag_name' | sed 's/[^0-9\.\-]*//g'
1.8.1
```
output = chatgpt_... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-18 | Human: ping bbc.com
AI:
```
$ ping bbc.com
PING bbc.com (151.101.65.81): 56 data bytes
64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms
64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms
--- bbc.com ping statistics ---
3 packets tran... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-19 | Explore our current openings and apply today. We look forward to hearing from you.
```
output = chatgpt_chain.predict(human_input="curl https://chat.openai.com/chat")
print(output)
> Entering new LLMChain chain...
Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to b... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-20 | ```
Human: lynx https://www.deepmind.com/careers
AI:
```
$ lynx https://www.deepmind.com/careers
DeepMind Careers
Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.
We offer a range of exciting opportuni... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-21 | Prompt after formatting:
Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-li... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-22 | ```
$ curl https://chat.openai.com/chat
<html>
<head>
<title>OpenAI Chat</title>
</head>
<body>
<h1>Welcome to OpenAI Chat!</h1>
<p>
OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.
</p>
<p>
To get st... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-23 | }
```
output = chatgpt_chain.predict(human_input="""curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique cod... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-24 | Human: curl https://chat.openai.com/chat
AI:
```
$ curl https://chat.openai.com/chat
<html>
<head>
<title>OpenAI Chat</title>
</head>
<body>
<h1>Welcome to OpenAI Chat!</h1>
<p>
OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conve... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
f16ab044f37a-25 | }
```
Human: curl --header "Content-Type:application/json" --request POST --data '{"message": "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/chatgpt_clone.html |
e82627202501-0 | .ipynb
.pdf
How to use a timeout for the agent
How to use a timeout for the agent#
This notebook walks through how to cap an agent executor after a certain amount of time. This can be useful for safeguarding against long running agent runs.
from langchain.agents import load_tools
from langchain.agents import initialize... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/max_time_limit.html |
e82627202501-1 | Final Answer: foo
> Finished chain.
'foo'
Now let’s try it again with the max_execution_time=1 keyword argument. It now stops nicely after 1 second (only one iteration usually)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, max_execution_time=1)
agent.run(adversarial_pro... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/max_time_limit.html |
ed32cace0207-0 | .ipynb
.pdf
Handle Parsing Errors
Contents
Setup
Error
Default error handling
Custom Error Message
Custom Error Function
Handle Parsing Errors#
Occasionally the LLM cannot determine what step to take because it outputs format in incorrect form to be handled by the output parser. In this case, by default the agent err... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
ed32cace0207-1 | 22 response = json.loads(action.strip())
IndexError: list index out of range
During handling of the above exception, another exception occurred:
OutputParserException Traceback (most recent call last)
Cell In[4], line 1
----> 1 mrkl.run("Who is Leo DiCaprio's girlfriend? No need to add Action")
... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
ed32cace0207-2 | 135 if new_arg_supported
136 else self._call(inputs)
137 )
138 except (KeyboardInterrupt, Exception) as e:
139 run_manager.on_chain_error(e)
File ~/workplace/langchain/langchain/agents/agent.py:947, in AgentExecutor._call(self, inputs, run_manager)
945 # We now enter the agen... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
ed32cace0207-3 | 758 Override this to take control of how the agent makes and acts on choices.
759 """
760 try:
761 # Call the LLM to see what to do.
--> 762 output = self.agent.plan(
763 intermediate_steps,
764 callbacks=run_manager.get_child() if run_manager else None,
765 **inp... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
ed32cace0207-4 | verbose=True,
handle_parsing_errors=True
)
mrkl.run("Who is Leo DiCaprio's girlfriend? No need to add Action")
> Entering new AgentExecutor chain...
Observation: Invalid or incomplete response
Thought:
Observation: Invalid or incomplete response
Thought:Search for Leo DiCaprio's current girlfriend
Action:
```
{
"... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
ed32cace0207-5 | "action_input": "Who is Leo DiCaprio's girlfriend?"
}
```
Observation: DiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spott... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
ed32cace0207-6 | "action_input": "Who is Leo DiCaprio's girlfriend?"
}
```
Observation: DiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spott... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/handle_parsing_errors.html |
c2957f083dfe-0 | .ipynb
.pdf
How to use the async API for Agents
Contents
Serial vs. Concurrent Execution
How to use the async API for Agents#
LangChain provides async support for Agents by leveraging the asyncio library.
Async methods are currently supported for the following Tools: GoogleSerperAPIWrapper, SerpAPIWrapper and LLMMath... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-1 | ]
llm = OpenAI(temperature=0)
tools = load_tools(["google-serper", "llm-math"], llm=llm)
agent = initialize_agent(
tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)
s = time.perf_counter()
for q in questions:
agent.run(q)
elapsed = time.perf_counter() - s
print(f"Serial executed in {elapse... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-2 | Observation: Rafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ... Draw: 128 (16 Q / 8 WC). Champion: Rafael Nadal. Runner-up: Daniil Medvedev. Score: 7–5, 6–3, 5–7, 4–6, 6–4. Bianca Andreescu won the women's singl... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-3 | Daniil Medvedev in the men's singles final of the U.S. Open on Sunday. Rafael Nadal survived. The 33-year-old defeated Daniil Medvedev in the final of the 2019 U.S. Open to earn his 19th Grand Slam title Sunday ... NEW YORK -- Rafael Nadal defeated Daniil Medvedev in an epic five-set match, 7-5, 6-3, 5-7, 4-6, 6-4 to w... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-4 | Thought: I now know that Rafael Nadal won the US Open men's final in 2019 and he is 33 years old.
Action: Calculator
Action Input: 33^0.334
Observation: Answer: 3.215019829667466
Thought: I now know the final answer.
Final Answer: Rafael Nadal won the US Open men's final in 2019 and his age raised to the 0.334 power is... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-5 | Action: Google Serper
Action Input: "who won the most recent formula 1 grand prix"
Observation: Max Verstappen won his first Formula 1 world title on Sunday after the championship was decided by a last-lap overtake of his rival Lewis Hamilton in the Abu Dhabi Grand Prix. Dec 12, 2021
Thought: I need to find out Max Ver... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-6 | Observation: Answer: 2.7212987634680084
Thought: I now know the final answer.
Final Answer: Nineteen-year-old Canadian Bianca Andreescu won the US Open women's final in 2019 and her age raised to the 0.34 power is 2.7212987634680084.
> Finished chain.
> Entering new AgentExecutor chain...
I need to find out who Beyonc... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-7 | await asyncio.gather(*tasks)
elapsed = time.perf_counter() - s
print(f"Concurrent executed in {elapsed:0.2f} seconds.")
> Entering new AgentExecutor chain...
> Entering new AgentExecutor chain...
> Entering new AgentExecutor chain...
> Entering new AgentExecutor chain...
> Entering new AgentExecutor chain...
I need to... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-8 | Thought:
Observation: Jay-Z
Thought: | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-9 | Observation: Rafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ... Draw: 128 (16 Q / 8 WC). Champion: Rafael Nadal. Runner-up: Daniil Medvedev. Score: 7–5, 6–3, 5–7, 4–6, 6–4. Bianca Andreescu won the women's singl... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-10 | Daniil Medvedev in the men's singles final of the U.S. Open on Sunday. Rafael Nadal survived. The 33-year-old defeated Daniil Medvedev in the final of the 2019 U.S. Open to earn his 19th Grand Slam title Sunday ... NEW YORK -- Rafael Nadal defeated Daniil Medvedev in an epic five-set match, 7-5, 6-3, 5-7, 4-6, 6-4 to w... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-11 | Thought:
Observation: WHAT HAPPENED: #SheTheNorth? She the champion. Nineteen-year-old Canadian Bianca Andreescu sealed her first Grand Slam title on Saturday, downing 23-time major champion Serena Williams in the 2019 US Open women's singles final, 6-3, 7-5. Sep 7, 2019
Thought: | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-12 | Thought:
Observation: Lewis Hamilton holds the record for the most race wins in Formula One history, with 103 wins to date. Michael Schumacher, the previous record holder, ... Michael Schumacher (top left) and Lewis Hamilton (top right) have each won the championship a record seven times during their careers, while Seb... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-13 | Action Input: "Harry Styles age" I need to find out Jay-Z's age
Action: Google Serper
Action Input: "How old is Jay-Z?" I now know that Rafael Nadal won the US Open men's final in 2019 and he is 33 years old.
Action: Calculator
Action Input: 33^0.334 I now need to calculate her age raised to the 0.34 power.
Action: Cal... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c2957f083dfe-14 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
71392c374e26-0 | .ipynb
.pdf
How to combine agents and vectorstores
Contents
Create the Vectorstore
Create the Agent
Use the Agent solely as a router
Multi-Hop vectorstore reasoning
How to combine agents and vectorstores#
This notebook covers how to combine agents and vectorstores. The use case for this is that you’ve ingested your d... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
71392c374e26-1 | texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
docsearch = Chroma.from_documents(texts, embeddings, collection_name="state-of-union")
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
state_of_union = RetrievalQA.from_chain_type(llm=llm... | https://python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.