id stringlengths 14 16 | text stringlengths 29 2.73k | source stringlengths 50 116 |
|---|---|---|
1b54f3692ba3-1 | 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 |
1b54f3692ba3-2 | 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 |
1b54f3692ba3-3 | 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 |
1b54f3692ba3-4 | 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 |
1b54f3692ba3-5 | 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 |
1b54f3692ba3-6 | 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 |
1b54f3692ba3-7 | 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 |
1b54f3692ba3-8 | 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 |
1b54f3692ba3-9 | 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 |
1b54f3692ba3-10 | 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 |
1b54f3692ba3-11 | 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 |
1b54f3692ba3-12 | 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 |
f4c86f023527-0 | .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 |
f4c86f023527-1 | 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 |
f4c86f023527-2 | 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 |
f4c86f023527-3 | 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 |
f4c86f023527-4 | 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 |
f4c86f023527-5 | 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 |
f4c86f023527-6 | 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 |
f4c86f023527-7 | 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 |
f4c86f023527-8 | 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 |
f4c86f023527-9 | 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 |
f4c86f023527-10 | 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 |
f4c86f023527-11 | 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 |
f4c86f023527-12 | 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 |
f4c86f023527-13 | 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 |
f4c86f023527-14 | 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 |
f4c86f023527-15 | --- 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 |
f4c86f023527-16 | 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 |
f4c86f023527-17 | ```
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 |
f4c86f023527-18 | 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 |
f4c86f023527-19 | 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 |
f4c86f023527-20 | ```
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 |
f4c86f023527-21 | 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 |
f4c86f023527-22 | ```
$ 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 |
f4c86f023527-23 | }
```
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 |
f4c86f023527-24 | 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 |
f4c86f023527-25 | }
```
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 |
a2d96cfe6138-0 | .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 |
a2d96cfe6138-1 | 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 |
c41cb8ca22ca-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: SerpAPIWrapper and LLMMathChain. Async support for... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c41cb8ca22ca-1 | ]
llm = OpenAI(temperature=0)
tools = load_tools(["llm-math", "serpapi"], 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 {elapsed:0.2f... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c41cb8ca22ca-2 | > Finished chain.
> Entering new AgentExecutor chain...
I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.
Action: Search
Action Input: "Olivia Wilde boyfriend"
Observation: Olivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sud... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c41cb8ca22ca-3 | Thought: I now know the final answer
Final Answer: Michael Schumacher, aged 54, raised to the 0.23 power is 2.502940725307012.
> Finished chain.
> Entering new AgentExecutor chain...
I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.
Action: Search
Action ... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c41cb8ca22ca-4 | Thought: I now know the final answer
Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.
> Finished chain.
Serial executed in 52.47 seconds.
llm = OpenAI(temperature=0)
tools = load_tools(["llm-math", "serpapi"], llm=llm)
agent = initialize_agent(
tools, llm, agent=Age... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c41cb8ca22ca-5 | Action: Search
Action Input: "US Open men's final 2019 winner"
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 ...
Thought: I need to find out who Olivia Wilde's boyfriend is and then calculate his a... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c41cb8ca22ca-6 | Thought: I need to calculate her age raised to the 0.34 power
Action: Calculator
Action Input: 22^0.34 I need to calculate 53 raised to the 0.19 power
Action: Calculator
Action Input: 53^0.19 I need to calculate 29 raised to the 0.23 power.
Action: Calculator
Action Input: 29^0.23 I need to find out the age of the winn... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
c41cb8ca22ca-7 | Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/async_agent.html |
44ae69215ad3-0 | .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 |
44ae69215ad3-1 | 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 |
44ae69215ad3-2 | ),
]
# Construct the agent. We will use the default agent type here.
# See documentation for a full list of options.
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("What did biden say about ketanji brown jackson is the state of the union address?")
> Entering n... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
44ae69215ad3-3 | Action Input: What are the advantages of using ruff over flake8?
Observation: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quali... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
44ae69215ad3-4 | Notice that in the above examples the agent did some extra work after querying the RetrievalQAChain. You can avoid that and just return the result directly.
tools = [
Tool(
name = "State of Union QA System",
func=state_of_union.run,
description="useful for when you need to answer questions a... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
44ae69215ad3-5 | Action Input: What are the advantages of using ruff over flake8?
Observation: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quali... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
44ae69215ad3-6 | Tool(
name = "Ruff QA System",
func=ruff.run,
description="useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before."
),
]
# Construct the agent. We will use the defau... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
44ae69215ad3-7 | previous
Agent Executors
next
How to use the async API for Agents
Contents
Create the Vectorstore
Create the Agent
Use the Agent solely as a router
Multi-Hop vectorstore reasoning
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/agent_vectorstore.html |
de7be484e8c1-0 | .ipynb
.pdf
How to access intermediate steps
How to access intermediate steps#
In order to get more visibility into what an agent is doing, we can also return intermediate steps. This comes in the form of an extra key in the return value, which is a list of (action, observation) tuples.
from langchain.agents import loa... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/intermediate_steps.html |
de7be484e8c1-1 | > Finished chain.
# The actual return type is a NamedTuple for the agent action, and then an observation
print(response["intermediate_steps"])
[(AgentAction(tool='Search', tool_input='Leo DiCaprio girlfriend', log=' I should look up who Leo DiCaprio is dating\nAction: Search\nAction Input: "Leo DiCaprio girlfriend"'), ... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/intermediate_steps.html |
de7be484e8c1-2 | ],
"Answer: 3.991298452658078\n"
]
]
previous
How to create ChatGPT Clone
next
How to cap the max number of iterations
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/intermediate_steps.html |
f8cb0df45527-0 | .ipynb
.pdf
How to cap the max number of iterations
How to cap the max number of iterations#
This notebook walks through how to cap an agent at taking a certain number of steps. This can be useful to ensure that they do not go haywire and take too many steps.
from langchain.agents import load_tools
from langchain.agent... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/max_iterations.html |
f8cb0df45527-1 | Final Answer: foo
> Finished chain.
'foo'
Now let’s try it again with the max_iterations=2 keyword argument. It now stops nicely after a certain amount of iterations!
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, max_iterations=2)
agent.run(adversarial_prompt)
> Enterin... | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/max_iterations.html |
f8cb0df45527-2 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/agents/agent_executors/examples/max_iterations.html |
ff8aa3da58f0-0 | .rst
.pdf
Text Embedding Models
Text Embedding Models#
Note
Conceptual Guide
This documentation goes over how to use the Embedding class in LangChain.
The Embedding class is a class designed for interfacing with embeddings. There are lots of Embedding providers (OpenAI, Cohere, Hugging Face, etc) - this class is design... | https:///python.langchain.com/en/latest/modules/models/text_embedding.html |
dc066d0022c7-0 | .rst
.pdf
LLMs
LLMs#
Note
Conceptual Guide
Large Language Models (LLMs) are a core component of LangChain.
LangChain is not a provider of LLMs, but rather provides a standard interface through which
you can interact with a variety of LLMs.
The following sections of documentation are provided:
Getting Started: An overvi... | https:///python.langchain.com/en/latest/modules/models/llms.html |
56f3e22bb85f-0 | .rst
.pdf
Chat Models
Chat Models#
Note
Conceptual Guide
Chat models are a variation on language models.
While chat models use language models under the hood, the interface they expose is a bit different.
Rather than expose a “text in, text out” API, they expose an interface where “chat messages” are the inputs and out... | https:///python.langchain.com/en/latest/modules/models/chat.html |
9d5945d24789-0 | .ipynb
.pdf
Sentence Transformers Embeddings
Sentence Transformers Embeddings#
SentenceTransformers embeddings are called using the HuggingFaceEmbeddings integration. We have also added an alias for SentenceTransformerEmbeddings for users who are more familiar with directly using that package.
SentenceTransformers is a... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/sentence_transformers.html |
c9521a55c862-0 | .ipynb
.pdf
TensorflowHub
TensorflowHub#
Let’s load the TensorflowHub Embedding class.
from langchain.embeddings import TensorflowHubEmbeddings
embeddings = TensorflowHubEmbeddings()
2023-01-30 23:53:01.652176: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neu... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/tensorflowhub.html |
1354c03ac35e-0 | .ipynb
.pdf
SageMaker Endpoint Embeddings
SageMaker Endpoint Embeddings#
Let’s load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.
For instructions on how to do this, please see here. Note: In order to handle batched requests, you will need to... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/sagemaker-endpoint.html |
1354c03ac35e-1 | query_result = embeddings.embed_query("foo")
doc_results = embeddings.embed_documents(["foo"])
doc_results
previous
OpenAI
next
Self Hosted Embeddings
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/sagemaker-endpoint.html |
5b21c5d1fec9-0 | .ipynb
.pdf
InstructEmbeddings
InstructEmbeddings#
Let’s load the HuggingFace instruct Embeddings class.
from langchain.embeddings import HuggingFaceInstructEmbeddings
embeddings = HuggingFaceInstructEmbeddings(
query_instruction="Represent the query for retrieval: "
)
load INSTRUCTOR_Transformer
max_seq_length 51... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/instruct_embeddings.html |
8aab9f71d72e-0 | .ipynb
.pdf
Cohere
Cohere#
Let’s load the Cohere Embedding class.
from langchain.embeddings import CohereEmbeddings
embeddings = CohereEmbeddings(cohere_api_key=cohere_api_key)
text = "This is a test document."
query_result = embeddings.embed_query(text)
doc_result = embeddings.embed_documents([text])
previous
AzureOpe... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/cohere.html |
4626c70bf315-0 | .ipynb
.pdf
Aleph Alpha
Contents
Asymmetric
Symmetric
Aleph Alpha#
There are two possible ways to use Aleph Alpha’s semantic embeddings. If you have texts with a dissimilar structure (e.g. a Document and a Query) you would want to use asymmetric embeddings. Conversely, for texts with comparable structures, symmetric ... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/aleph_alpha.html |
fd614016e339-0 | .ipynb
.pdf
AzureOpenAI
AzureOpenAI#
Let’s load the OpenAI Embedding class with environment variables set to indicate to use Azure endpoints.
# set the environment variables needed for openai package to know to reach out to azure
import os
os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["OPENAI_API_BASE"] = "https:/... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/azureopenai.html |
e9fb978e8ebe-0 | .ipynb
.pdf
Fake Embeddings
Fake Embeddings#
LangChain also provides a fake embedding class. You can use this to test your pipelines.
from langchain.embeddings import FakeEmbeddings
embeddings = FakeEmbeddings(size=1352)
query_result = embeddings.embed_query("foo")
doc_results = embeddings.embed_documents(["foo"])
prev... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/fake.html |
df14706483d9-0 | .ipynb
.pdf
Llama-cpp
Llama-cpp#
This notebook goes over how to use Llama-cpp embeddings within LangChain
!pip install llama-cpp-python
from langchain.embeddings import LlamaCppEmbeddings
llama = LlamaCppEmbeddings(model_path="/path/to/model/ggml-model-q4_0.bin")
text = "This is a test document."
query_result = llama.e... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/llamacpp.html |
19ac4b46d863-0 | .ipynb
.pdf
Self Hosted Embeddings
Self Hosted Embeddings#
Let’s load the SelfHostedEmbeddings, SelfHostedHuggingFaceEmbeddings, and SelfHostedHuggingFaceInstructEmbeddings classes.
from langchain.embeddings import (
SelfHostedEmbeddings,
SelfHostedHuggingFaceEmbeddings,
SelfHostedHuggingFaceInstructEmbeddi... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/self-hosted.html |
19ac4b46d863-1 | tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
return pipeline("feature-extraction", model=model, tokenizer=tokenizer)
def inference_fn(pipeline, prompt):
# Return last hidden state of the model
if isinstance(prompt, list):
return [emb[... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/self-hosted.html |
04f2d69cf4d1-0 | .ipynb
.pdf
Hugging Face Hub
Hugging Face Hub#
Let’s load the Hugging Face Embedding class.
from langchain.embeddings import HuggingFaceEmbeddings
embeddings = HuggingFaceEmbeddings()
text = "This is a test document."
query_result = embeddings.embed_query(text)
doc_result = embeddings.embed_documents([text])
previous
F... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/huggingfacehub.html |
bc8e1b19f69b-0 | .ipynb
.pdf
Jina
Jina#
Let’s load the Jina Embedding class.
from langchain.embeddings import JinaEmbeddings
embeddings = JinaEmbeddings(jina_auth_token=jina_auth_token, model_name="ViT-B-32::openai")
text = "This is a test document."
query_result = embeddings.embed_query(text)
doc_result = embeddings.embed_documents([t... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/jina.html |
8dd53b89bc43-0 | .ipynb
.pdf
OpenAI
OpenAI#
Let’s load the OpenAI Embedding class.
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
text = "This is a test document."
query_result = embeddings.embed_query(text)
doc_result = embeddings.embed_documents([text])
Let’s load the OpenAI Embedding class with fir... | https:///python.langchain.com/en/latest/modules/models/text_embedding/examples/openai.html |
aa3c07c6d8c7-0 | .rst
.pdf
How-To Guides
How-To Guides#
The examples here all address certain “how-to” guides for working with chat models.
How to use few shot examples
How to stream responses
previous
Getting Started
next
How to use few shot examples
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated ... | https:///python.langchain.com/en/latest/modules/models/chat/how_to_guides.html |
4c1121a0996b-0 | .ipynb
.pdf
Getting Started
Contents
PromptTemplates
LLMChain
Streaming
Getting Started#
This notebook covers how to get started with chat models. The interface is based around messages rather than raw text.
from langchain.chat_models import ChatOpenAI
from langchain import PromptTemplate, LLMChain
from langchain.pro... | https:///python.langchain.com/en/latest/modules/models/chat/getting_started.html |
4c1121a0996b-1 | [
SystemMessage(content="You are a helpful assistant that translates English to French."),
HumanMessage(content="Translate this sentence from English to French. I love programming.")
],
[
SystemMessage(content="You are a helpful assistant that translates English to French."),
Hum... | https:///python.langchain.com/en/latest/modules/models/chat/getting_started.html |
4c1121a0996b-2 | system_message_prompt = SystemMessagePromptTemplate.from_template(template)
human_template="{text}"
human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)
chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])
# get a chat completion from the formatted mes... | https:///python.langchain.com/en/latest/modules/models/chat/getting_started.html |
4c1121a0996b-3 | A drink that's always on my mind
With every sip, I feel alive
Sparkling water, you're my vibe
Verse 2:
No sugar, no calories, just pure bliss
A drink that's hard to resist
It's the perfect way to quench my thirst
A drink that always comes first
Chorus:
Sparkling water, oh so fine
A drink that's always on my mind
With e... | https:///python.langchain.com/en/latest/modules/models/chat/getting_started.html |
9d61c5046a2a-0 | .rst
.pdf
Integrations
Integrations#
The examples here all highlight how to integrate with different chat models.
Anthropic
Azure
OpenAI
PromptLayer ChatOpenAI
previous
How to stream responses
next
Anthropic
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/models/chat/integrations.html |
7fed9917aaca-0 | .ipynb
.pdf
PromptLayer ChatOpenAI
Contents
Install PromptLayer
Imports
Set the Environment API Key
Use the PromptLayerOpenAI LLM like normal
Using PromptLayer Track
PromptLayer ChatOpenAI#
This example showcases how to connect to PromptLayer to start recording your ChatOpenAI requests.
Install PromptLayer#
The promp... | https:///python.langchain.com/en/latest/modules/models/chat/integrations/promptlayer_chatopenai.html |
7fed9917aaca-1 | chat = PromptLayerChatOpenAI(return_pl_id=True)
chat_results = chat.generate([[HumanMessage(content="I am a cat and I want")]])
for res in chat_results.generations:
pl_request_id = res[0].generation_info["pl_request_id"]
promptlayer.track.score(request_id=pl_request_id, score=100)
Using this allows you to track... | https:///python.langchain.com/en/latest/modules/models/chat/integrations/promptlayer_chatopenai.html |
f36b1a651334-0 | .ipynb
.pdf
Azure
Azure#
This notebook goes over how to connect to an Azure hosted OpenAI endpoint
from langchain.chat_models import AzureChatOpenAI
from langchain.schema import HumanMessage
BASE_URL = "https://${TODO}.openai.azure.com"
API_KEY = "..."
DEPLOYMENT_NAME = "chat"
model = AzureChatOpenAI(
openai_api_ba... | https:///python.langchain.com/en/latest/modules/models/chat/integrations/azure_chat_openai.html |
21f49a0bd4a9-0 | .ipynb
.pdf
Anthropic
Contents
ChatAnthropic also supports async and streaming functionality:
Anthropic#
This notebook covers how to get started with Anthropic chat models.
from langchain.chat_models import ChatAnthropic
from langchain.prompts.chat import (
ChatPromptTemplate,
SystemMessagePromptTemplate,
... | https:///python.langchain.com/en/latest/modules/models/chat/integrations/anthropic.html |
4d52752cd681-0 | .ipynb
.pdf
OpenAI
OpenAI#
This notebook covers how to get started with OpenAI chat models.
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
ChatPromptTemplate,
SystemMessagePromptTemplate,
AIMessagePromptTemplate,
HumanMessagePromptTemplate,
)
from langchain.schema impo... | https:///python.langchain.com/en/latest/modules/models/chat/integrations/openai.html |
4d52752cd681-1 | AIMessage(content="J'adore la programmation.", additional_kwargs={})
previous
Azure
next
PromptLayer ChatOpenAI
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/models/chat/integrations/openai.html |
d45faf2b7b47-0 | .ipynb
.pdf
How to stream responses
How to stream responses#
This notebook goes over how to use streaming with a chat model.
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
HumanMessage,
)
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
chat = ChatOpenAI(s... | https:///python.langchain.com/en/latest/modules/models/chat/examples/streaming.html |
d45faf2b7b47-1 | previous
How to use few shot examples
next
Integrations
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/models/chat/examples/streaming.html |
fb9cd7ca768d-0 | .ipynb
.pdf
How to use few shot examples
Contents
Alternating Human/AI messages
System Messages
How to use few shot examples#
This notebook covers how to use few shot examples in chat models.
There does not appear to be solid consensus on how best to do few shot prompting. As a result, we are not solidifying any abst... | https:///python.langchain.com/en/latest/modules/models/chat/examples/few_shot_examples.html |
fb9cd7ca768d-1 | template="You are a helpful assistant that translates english to pirate."
system_message_prompt = SystemMessagePromptTemplate.from_template(template)
example_human = SystemMessagePromptTemplate.from_template("Hi", additional_kwargs={"name": "example_user"})
example_ai = SystemMessagePromptTemplate.from_template("Argh m... | https:///python.langchain.com/en/latest/modules/models/chat/examples/few_shot_examples.html |
97f06f1eb7d4-0 | .rst
.pdf
Generic Functionality
Generic Functionality#
The examples here all address certain “how-to” guides for working with LLMs.
How to use the async API for LLMs
How to write a custom LLM wrapper
How (and why) to use the fake LLM
How to cache LLM calls
How to serialize LLM classes
How to stream LLM and Chat Model r... | https:///python.langchain.com/en/latest/modules/models/llms/how_to_guides.html |
7483212a5b12-0 | .ipynb
.pdf
Getting Started
Getting Started#
This notebook goes over how to use the LLM class in LangChain.
The LLM class is a class designed for interfacing with LLMs. There are lots of LLM providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them. In this p... | https:///python.langchain.com/en/latest/modules/models/llms/getting_started.html |
7483212a5b12-1 | llm_result.generations[-1]
[Generation(text="\n\nWhat if love neverspeech\n\nWhat if love never ended\n\nWhat if love was only a feeling\n\nI'll never know this love\n\nIt's not a feeling\n\nBut it's what we have for each other\n\nWe just know that love is something strong\n\nAnd we can't help but be happy\n\nWe just f... | https:///python.langchain.com/en/latest/modules/models/llms/getting_started.html |
7483212a5b12-2 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 02, 2023. | https:///python.langchain.com/en/latest/modules/models/llms/getting_started.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.