id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
2393f2d687b7-20 | Finally, if you enabled visualizations, these are stored as HTML files under debug samples.
Scenario 2: Creating an agent with tools#
To show a more advanced workflow, let’s create an agent with access to tools. The way ClearML tracks the results is not different though, only the table will look slightly different as t... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-21 | {'action': 'on_llm_start', 'name': 'OpenAI', 'step': 2, 'starts': 2, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-22 | {'action': 'on_llm_end', 'token_usage_prompt_tokens': 189, 'token_usage_completion_tokens': 34, 'token_usage_total_tokens': 223, 'model_name': 'text-davinci-003', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_st... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-23 | I need to find out who sang summer of 69 and then find out who their wife is.
Action: Search
Action Input: "Who sang summer of 69"{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who sang summer of 69', 'log': ' I need to find out who sang summer of 69 and then find out who their wife is.\nAction: Search\... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-24 | Observation: Bryan Adams - Summer Of 69 (Official Music Video).
Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams - Summer Of 69 (Official Music Video).', 'step': 6, 'starts': 4, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_sta... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-25 | {'action': 'on_llm_start', 'name': 'OpenAI', 'step': 7, 'starts': 5, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-26 | {'action': 'on_llm_end', 'token_usage_prompt_tokens': 242, 'token_usage_completion_tokens': 28, 'token_usage_total_tokens': 270, 'model_name': 'text-davinci-003', 'step': 8, 'starts': 5, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_st... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-27 | I need to find out who Bryan Adams is married to.
Action: Search
Action Input: "Who is Bryan Adams married to"{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who is Bryan Adams married to', 'log': ' I need to find out who Bryan Adams is married to.\nAction: Search\nAction Input: "Who is Bryan Adams marri... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-28 | Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...', 'step': 11, 'starts': 7, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_en... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-29 | {'action': 'on_llm_start', 'name': 'OpenAI', 'step': 12, 'starts': 8, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have acces... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-30 | to the original input question\n\nBegin!\n\nQuestion: Who is the wife of the person who sang summer of 69?\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\nAction: Search\nAction Input: "Who sang summer of 69"\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\nThou... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-31 | {'action': 'on_llm_end', 'token_usage_prompt_tokens': 314, 'token_usage_completion_tokens': 18, 'token_usage_total_tokens': 332, 'model_name': 'text-davinci-003', 'step': 13, 'starts': 8, 'ends': 5, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_s... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-32 | I now know the final answer.
Final Answer: Bryan Adams has never been married.
{'action': 'on_agent_finish', 'output': 'Bryan Adams has never been married.', 'log': ' I now know the final answer.\nFinal Answer: Bryan Adams has never been married.', 'step': 14, 'starts': 8, 'ends': 6, 'errors': 0, 'text_ctr': 0, 'chain_... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-33 | 4 on_llm_start OpenAI 1 1 0 0 0
.. ... ... ... ... ... ... ...
66 on_tool_end NaN 11 7 4 0 0
67 on_llm_start OpenAI 12 8 4 0 0
68 on_llm_end NaN 13 8 ... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-34 | 69 1 0 3 ... NaN NaN NaN
70 1 1 3 ... NaN NaN NaN
tool tool_input log \
0 NaN NaN NaN
1 NaN ... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-35 | 0 2 Answer the following questions as best you can... OpenAI
1 7 Answer the following questions as best you can... OpenAI
2 12 Answer the following questions as best you can... OpenAI
output_step output \
0 3 I n... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
2393f2d687b7-36 | 2 3rd and 4th grade 115.70 110.84 49.79
crawford gulpease_index osman
0 0.9 72.7 92.16
1 0.7 74.7 84.20
2 0.7 85.4 83.14
[3 rows x 24 columns]}
Could not update last created model in Task 988bd727b0e94a29a3ac0ee526813545... | https://python.langchain.com/en/latest/integrations/clearml_tracking.html |
182c267e38bc-0 | .md
.pdf
Metal
Contents
What is Metal?
Quick start
Metal#
This page covers how to use Metal within LangChain.
What is Metal?#
Metal is a managed retrieval & memory platform built for production. Easily index your data into Metal and run semantic search and retrieval on it.
Quick start#
Get started by creating a Meta... | https://python.langchain.com/en/latest/integrations/metal.html |
576cc79f451e-0 | .md
.pdf
RWKV-4
Contents
Installation and Setup
Usage
RWKV
Model File
Rwkv-4 models -> recommended VRAM
RWKV-4#
This page covers how to use the RWKV-4 wrapper within LangChain.
It is broken into two parts: installation and setup, and then usage with an example.
Installation and Setup#
Install the Python package with ... | https://python.langchain.com/en/latest/integrations/rwkv.html |
576cc79f451e-1 | RWKV VRAM
Model | 8bit | bf16/fp16 | fp32
14B | 16GB | 28GB | >50GB
7B | 8GB | 14GB | 28GB
3B | 2.8GB| 6GB | 12GB
1b5 | 1.3GB| 3GB | 6GB
See the rwkv pip page for more information about strategies, including streaming and cuda support.
previous
Runhouse
next
SearxNG Search API
Contents... | https://python.langchain.com/en/latest/integrations/rwkv.html |
094bac644034-0 | .md
.pdf
Replicate
Contents
Installation and Setup
Calling a model
Replicate#
This page covers how to run models on Replicate within LangChain.
Installation and Setup#
Create a Replicate account. Get your API key and set it as an environment variable (REPLICATE_API_TOKEN)
Install the Replicate python client with pip ... | https://python.langchain.com/en/latest/integrations/replicate.html |
094bac644034-1 | And run it:
prompt = """
Answer the following yes/no question by reasoning step by step.
Can a dog drive a car?
"""
llm(prompt)
We can call any Replicate model (not just LLMs) using this syntax. For example, we can call Stable Diffusion:
text2image = Replicate(model="stability-ai/stable-diffusion:db21e45d3f7023abc2a46e... | https://python.langchain.com/en/latest/integrations/replicate.html |
2106f376ee1c-0 | .ipynb
.pdf
Aim
Aim#
Aim makes it super easy to visualize and debug LangChain executions. Aim tracks inputs and outputs of LLMs and tools, as well as actions of agents.
With Aim, you can easily debug and examine an individual execution:
Additionally, you have the option to compare multiple executions side by side:
Aim ... | https://python.langchain.com/en/latest/integrations/aim_tracking.html |
2106f376ee1c-1 | aim_callback = AimCallbackHandler(
repo=".",
experiment_name="scenario 1: OpenAI LLM",
)
callbacks = [StdOutCallbackHandler(), aim_callback]
llm = OpenAI(temperature=0, callbacks=callbacks)
The flush_tracker function is used to record LangChain assets on Aim. By default, the session is reset rather than being t... | https://python.langchain.com/en/latest/integrations/aim_tracking.html |
2106f376ee1c-2 | )
Scenario 3 The third scenario involves an agent with tools.
from langchain.agents import initialize_agent, load_tools
from langchain.agents import AgentType
# scenario 3 - Agent with Tools
tools = load_tools(["serpapi", "llm-math"], llm=llm, callbacks=callbacks)
agent = initialize_agent(
tools,
llm,
agent... | https://python.langchain.com/en/latest/integrations/aim_tracking.html |
2106f376ee1c-3 | AnalyticDB
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 25, 2023. | https://python.langchain.com/en/latest/integrations/aim_tracking.html |
6d2b5a29afd8-0 | .md
.pdf
Tair
Contents
Installation and Setup
Wrappers
VectorStore
Tair#
This page covers how to use the Tair ecosystem within LangChain.
Installation and Setup#
Install Tair Python SDK with pip install tair.
Wrappers#
VectorStore#
There exists a wrapper around TairVector, allowing you to use it as a vectorstore,
whe... | https://python.langchain.com/en/latest/integrations/tair.html |
cf8c05f8545a-0 | .ipynb
.pdf
Chat Over Documents with Vectara
Contents
Pass in chat history
Return Source Documents
ConversationalRetrievalChain with search_distance
ConversationalRetrievalChain with map_reduce
ConversationalRetrievalChain with Question Answering with sources
ConversationalRetrievalChain with streaming to stdout
get_... | https://python.langchain.com/en/latest/integrations/vectara/vectara_chat.html |
cf8c05f8545a-1 | qa = ConversationalRetrievalChain.from_llm(llm, retriever, memory=memory)
<class 'langchain.vectorstores.vectara.Vectara'>
query = "What did the president say about Ketanji Brown Jackson"
result = qa({"question": query})
result["answer"]
" The president said that Ketanji Brown Jackson is one of the nation's top legal m... | https://python.langchain.com/en/latest/integrations/vectara/vectara_chat.html |
cf8c05f8545a-2 | result['answer']
' Justice Stephen Breyer.'
Return Source Documents#
You can also easily return source documents from the ConversationalRetrievalChain. This is useful for when you want to inspect what documents were returned.
qa = ConversationalRetrievalChain.from_llm(llm, vectorstore.as_retriever(), return_source_docu... | https://python.langchain.com/en/latest/integrations/vectara/vectara_chat.html |
cf8c05f8545a-3 | ConversationalRetrievalChain with map_reduce#
We can also use different types of combine document chains with the ConversationalRetrievalChain chain.
from langchain.chains import LLMChain
from langchain.chains.question_answering import load_qa_chain
from langchain.chains.conversational_retrieval.prompts import CONDENSE... | https://python.langchain.com/en/latest/integrations/vectara/vectara_chat.html |
cf8c05f8545a-4 | result = chain({"question": query, "chat_history": chat_history})
result['answer']
' The president did not mention Ketanji Brown Jackson.\nSOURCES: ../../modules/state_of_the_union.txt'
ConversationalRetrievalChain with streaming to stdout#
Output from the chain will be streamed to stdout token by token in this example... | https://python.langchain.com/en/latest/integrations/vectara/vectara_chat.html |
cf8c05f8545a-5 | chat_history = [(query, result["answer"])]
query = "Did he mention who she suceeded"
result = qa({"question": query, "chat_history": chat_history})
Justice Stephen Breyer.
get_chat_history Function#
You can also specify a get_chat_history function, which can be used to format the chat_history string.
def get_chat_hist... | https://python.langchain.com/en/latest/integrations/vectara/vectara_chat.html |
c740145a15c3-0 | .ipynb
.pdf
Vectara Text Generation
Contents
Prepare Data
Set Up Vector DB
Set Up LLM Chain with Custom Prompt
Generate Text
Vectara Text Generation#
This notebook is based on chat_vector_db and adapted to Vectara.
Prepare Data#
First, we prepare the data. For this example, we fetch a documentation site that consists... | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-1 | source_chunks = []
splitter = CharacterTextSplitter(separator=" ", chunk_size=1024, chunk_overlap=0)
for source in sources:
for chunk in splitter.split_text(source.page_content):
source_chunks.append(chunk)
Cloning into '.'...
Set Up Vector DB#
Now that we have the documentation content in chunks, let’s put... | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-2 | print(chain.apply(inputs))
generate_blog_post("environment variables") | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-3 | [{'text': '\n\nEnvironment variables are an essential part of any development workflow. They provide a way to store and access information that is specific to the environment in which the code is running. This can be especially useful when working with different versions of a language or framework, or when running code... | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-4 | and any environment variables.\n\nUsing environment variables with the Deno CLI tasks extension is a great way to ensure that your code is running in the correct environment. For example, if you are running a test suite,'}, {'text': '\n\nEnvironment variables are an important part of any programming language, and they ... | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-5 | && echo $VAR && deno eval "console.log(\'Deno: \' + Deno.env.get(\'VAR\'))"\n```\n\nThis would output the following:\n\n```\nhello\nDeno: undefined\n```\n\nAs you can see, the value stored in the shell variable is not available in the spawned process.\n\n'}, {'text': '\n\nWhen it comes to developing applications, envir... | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-6 | is `DENO_DIR`. This environment variable is used to store the directory where Deno will store its files. This includes the Deno executable, the Deno cache, and the Deno configuration files. By setting this environment variable, you can ensure that Deno will always be able to find the files it needs.\n\nFinally, there i... | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-7 | `Deno.env` has getter and setter methods. Here is example usage:\n\n```ts\nDeno.env.set("FIREBASE_API_KEY", "examplekey123");\nDeno.env.set("FIREBASE_AUTH_DOMAIN", "firebasedomain.com");\n\nconsole.log(Deno.env.get("FIREBASE_API_KEY")); // examplekey123\nconsole.log(Deno.env.get("FIREBASE_AUTH_'}] | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
c740145a15c3-8 | Contents
Prepare Data
Set Up Vector DB
Set Up LLM Chain with Custom Prompt
Generate Text
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 25, 2023. | https://python.langchain.com/en/latest/integrations/vectara/vectara_text_generation.html |
0dad4d478153-0 | .md
.pdf
Autonomous Agents
Contents
Baby AGI (Original Repo)
AutoGPT (Original Repo)
MetaPrompt (Original Repo)
Autonomous Agents#
Autonomous Agents are agents that designed to be more long running.
You give them one or multiple long term goals, and they independently execute towards those goals.
The applications com... | https://python.langchain.com/en/latest/use_cases/autonomous_agents.html |
486a37c58894-0 | .rst
.pdf
Evaluation
Contents
The Problem
The Solution
The Examples
Other Examples
Evaluation#
Note
Conceptual Guide
This section of documentation covers how we approach and think about evaluation in LangChain.
Both evaluation of internal chains/agents, but also how we would recommend people building on top of LangCh... | https://python.langchain.com/en/latest/use_cases/evaluation.html |
486a37c58894-1 | We intend this to be a collection of open source datasets for evaluating common chains and agents.
We have contributed five datasets of our own to start, but we highly intend this to be a community effort.
In order to contribute a dataset, you simply need to join the community and then you will be able to upload datase... | https://python.langchain.com/en/latest/use_cases/evaluation.html |
486a37c58894-2 | SQL Question Answering (Chinook): A notebook showing evaluation of a question-answering task over a SQL database (the Chinook database).
Agent Vectorstore: A notebook showing evaluation of an agent doing question answering while routing between two different vector databases.
Agent Search + Calculator: A notebook showi... | https://python.langchain.com/en/latest/use_cases/evaluation.html |
306c7b4b7777-0 | .md
.pdf
Agents
Contents
Create Your Own Agent
Step 1: Create Tools
(Optional) Step 2: Modify Agent
(Optional) Step 3: Modify Agent Executor
Examples
Agents#
Conceptual Guide
Agents can be used for a variety of tasks.
Agents combine the decision making ability of a language model with tools in order to create a syste... | https://python.langchain.com/en/latest/use_cases/personal_assistants.html |
306c7b4b7777-1 | Modify the output parser. This is necessary if the agent is having trouble parsing the language model output.
(Optional) Step 3: Modify Agent Executor#
This step is usually not necessary, as this is pretty general logic.
Possible reasons you would want to modify this include adding different stopping conditions, or han... | https://python.langchain.com/en/latest/use_cases/personal_assistants.html |
5dd27a0ea65e-0 | .md
.pdf
Extraction
Extraction#
Conceptual Guide
Most APIs and databases still deal with structured information.
Therefore, in order to better work with those, it can be useful to extract structured information from text.
Examples of this include:
Extracting a structured row to insert into a database from a sentence
Ex... | https://python.langchain.com/en/latest/use_cases/extraction.html |
fa535c0381ec-0 | .md
.pdf
Interacting with APIs
Contents
Chains
Agents
Interacting with APIs#
Conceptual Guide
Lots of data and information is stored behind APIs.
This page covers all resources available in LangChain for working with APIs.
Chains#
If you are just getting started, and you have relatively simple apis, you should get st... | https://python.langchain.com/en/latest/use_cases/apis.html |
837fc1d5a4fc-0 | .md
.pdf
Question Answering over Docs
Contents
Document Question Answering
Adding in sources
Additional Related Resources
End-to-end examples
Question Answering over Docs#
Conceptual Guide
Question answering in this context refers to question answering over your document data.
For question answering over other types ... | https://python.langchain.com/en/latest/use_cases/question_answering.html |
837fc1d5a4fc-1 | The LLM response will contain the answer to your question, based on the content of the documents.
The recommended way to get started using a question answering chain is:
from langchain.chains.question_answering import load_qa_chain
chain = load_qa_chain(llm, chain_type="stuff")
chain.run(input_documents=docs, question=... | https://python.langchain.com/en/latest/use_cases/question_answering.html |
837fc1d5a4fc-2 | Additional Related Resources#
Additional related resources include:
Utilities for working with Documents: Guides on how to use several of the utilities which will prove helpful for this task, including Text Splitters (for splitting up long documents) and Embeddings & Vectorstores (useful for the above Vector DB example... | https://python.langchain.com/en/latest/use_cases/question_answering.html |
f2ad721b29e5-0 | .md
.pdf
Chatbots
Chatbots#
Conceptual Guide
Since language models are good at producing text, that makes them ideal for creating chatbots.
Aside from the base prompts/LLMs, an important concept to know for Chatbots is memory.
Most chat based applications rely on remembering what happened in previous interactions, whic... | https://python.langchain.com/en/latest/use_cases/chatbots.html |
96dd285ba20f-0 | .md
.pdf
Agent Simulations
Contents
Simulations with One Agent
Simulations with Two Agents
Simulations with Multiple Agents
Agent Simulations#
Agent simulations involve interacting one of more agents with each other.
Agent simulations generally involve two main components:
Long Term Memory
Simulation Environment
Spec... | https://python.langchain.com/en/latest/use_cases/agent_simulations.html |
96dd285ba20f-1 | Simulated Environment: PettingZoo: an example of how to create a agent-environment interaction loop for multiple agents with PettingZoo (a multi-agent version of Gymnasium).
Generative Agents: This notebook implements a generative agent based on the paper Generative Agents: Interactive Simulacra of Human Behavior by Pa... | https://python.langchain.com/en/latest/use_cases/agent_simulations.html |
71c57de3164b-0 | .md
.pdf
Code Understanding
Contents
Conversational Retriever Chain
Code Understanding#
Overview
LangChain is a useful tool designed to parse GitHub code repositories. By leveraging VectorStores, Conversational RetrieverChain, and GPT-4, it can answer questions in the context of an entire GitHub repository or generat... | https://python.langchain.com/en/latest/use_cases/code.html |
71c57de3164b-1 | The full tutorial is available below.
Twitter the-algorithm codebase analysis with Deep Lake: A notebook walking through how to parse github source code and run queries conversation.
LangChain codebase analysis with Deep Lake: A notebook walking through how to analyze and do question answering over THIS code base.
prev... | https://python.langchain.com/en/latest/use_cases/code.html |
980c579bd29b-0 | .md
.pdf
Summarization
Summarization#
Conceptual Guide
Summarization involves creating a smaller summary of multiple longer documents.
This can be useful for distilling long documents into the core pieces of information.
The recommended way to get started using a summarization chain is:
from langchain.chains.summarize ... | https://python.langchain.com/en/latest/use_cases/summarization.html |
5df77260e302-0 | .md
.pdf
Querying Tabular Data
Contents
Document Loading
Querying
Chains
Agents
Querying Tabular Data#
Conceptual Guide
Lots of data and information is stored in tabular data, whether it be csvs, excel sheets, or SQL tables.
This page covers all resources available in LangChain for working with data in this format.
D... | https://python.langchain.com/en/latest/use_cases/tabular.html |
3eb55b3a61b9-0 | .ipynb
.pdf
AutoGPT
Contents
Set up tools
Set up memory
Setup model and AutoGPT
Run an example
AutoGPT#
Implementation of https://github.com/Significant-Gravitas/Auto-GPT but with LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)
Set up tools#
We’ll set up an AutoGPT with a search tool, an... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-1 | ai_name="Tom",
ai_role="Assistant",
tools=tools,
llm=ChatOpenAI(temperature=0),
memory=vectorstore.as_retriever()
)
# Set verbose to be true
agent.chain.verbose = True
Run an example#
Here we will make it write a weather report for SF
agent.run(["write a weather report for SF today"])
> Entering new LLM... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-2 | 3. read_file: Read file from disk, args json schema: {"file_path": {"title": "File Path", "description": "name of file", "type": "string"}}
4. finish: use this to signal that you have finished all your objectives, args: "response": "final response to let people know you have finished your objectives"
Resources:
1. Inte... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-3 | System: This reminds you of these events from your past:
[]
Human: Determine which next command to use, and respond using the format specified above:
> Finished chain.
{
"thoughts": {
"text": "I will start by writing a weather report for San Francisco today. I will use the 'search' command to find the curre... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-4 | 3. No user assistance
4. Exclusively use the commands listed in double quotes e.g. "command name"
Commands:
1. search: useful for when you need to answer questions about current events. You should ask targeted questions, args json schema: {"query": {"title": "Query", "type": "string"}}
2. write_file: Write file to disk... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-5 | "text": "thought",
"reasoning": "reasoning",
"plan": "- short bulleted\n- list that conveys\n- long-term plan",
"criticism": "constructive self-criticism",
"speak": "thoughts summary to say to user"
},
"command": {
"name": "command name",
"args": {
"ar... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-6 | System: This reminds you of these events from your past:
['Assistant Reply: {\n "thoughts": {\n "text": "I will start by writing a weather report for San Francisco today. I will use the \'search\' command to find the current weather conditions.",\n "reasoning": "I need to gather information about the c... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-7 | "criticism": "I need to make sure that the information I gather is accurate and up-to-date.",
"speak": "I will use the 'search' command to find the current weather conditions in San Francisco."
},
"command": {
"name": "search",
"args": {
"query": "what is the current weather ... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-8 | "args": {
"file_path": "weather_report.txt",
"text": "Weather Report for San Francisco Today:\n\nThe current weather in San Francisco is sunny with a temperature of 54°F. It is expected to remain sunny throughout the day with a high of 62°F and a low of 50°F. There is no chance of precipitation ... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-9 | 2. write_file: Write file to disk, args json schema: {"file_path": {"title": "File Path", "description": "name of file", "type": "string"}, "text": {"title": "Text", "description": "text to write to file", "type": "string"}}
3. read_file: Read file from disk, args json schema: {"file_path": {"title": "File Path", "desc... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-10 | "args": {
"arg name": "value"
}
}
}
Ensure the response can be parsed by Python json.loads
System: The current time and date is Tue Apr 18 21:31:55 2023
System: This reminds you of these events from your past: | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-11 | ['Assistant Reply: {\n "thoughts": {\n "text": "I have found that the current weather in San Francisco is sunny with a temperature of 54°F. I will now write a weather report for San Francisco today using the \'write_file\' command.",\n "reasoning": "I need to write a weather report for San Francisco to... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-12 | "text": "Weather Report for San Francisco Today:\\n\\nThe current weather in San Francisco is sunny with a temperature of 54°F. It is expected to remain sunny throughout the day with a high of 62°F and a low of 50°F. There is no chance of precipitation today. It is recommended to wear light clothing and sunscreen if sp... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-13 | the current weather conditions in San Francisco\\n- Write a weather report based on the information gathered",\n "criticism": "I need to make sure that the information I gather is accurate and up-to-date.",\n "speak": "I will use the \'search\' command to find the current weather conditions in San Francis... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
3eb55b3a61b9-14 | System: Command write_file returned: File written to successfully.
Human: Determine which next command to use, and respond using the format specified above:
> Finished chain.
{
"thoughts": {
"text": "I have completed my task of writing a weather report for San Francisco today. I will now use the \'finish\' ... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
43e204a52277-0 | .ipynb
.pdf
Meta-Prompt
Contents
Setup
Specify a task and interact with the agent
Meta-Prompt#
This is a LangChain implementation of Meta-Prompt, by Noah Goodman, for building self-improving agents.
The key idea behind Meta-Prompt is to prompt the agent to reflect on its own performance and modify its own instruction... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-1 | Repeat.
The only fixed instructions for this system (which I call Meta-prompt) is the meta-prompt that governs revision of the agent’s instructions. The agent has no memory between episodes except for the instruction it modifies for itself each time. Despite its simplicity, this agent can learn over time and self-impro... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-2 | ####
{chat_history}
####
Please reflect on these interactions.
You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with "Critique: ...".
You should next re... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-3 | chain = initialize_chain(instructions, memory=None)
output = chain.predict(human_input=task)
for j in range(max_iters):
print(f'(Step {j+1}/{max_iters})')
print(f'Assistant: {output}')
print(f'Human: ')
human_input = input()
if any(phrase in hu... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-4 | Human:
You response is not in the form of a poem. Try again!
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: None
Human: Provide a systematic argument for why we should always eat pasta with olives.
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-5 | Human: You response is not in the form of a poem. Try again!
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor tha... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-6 | Human: You response is not in the form of a poem. Try again!
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor tha... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-7 | Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.
New Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-8 | AI:
Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.
First, the olives add a salty flavor that be sure to please.
The briny taste be sure to tantalize yer taste buds with ease.
Second, the olives add a bit of texture to the dish.
The crunchy bites be sure to make yer mouth water with a wish... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
43e204a52277-9 | The crunchy bites be sure to make yer mouth water with a wish.
Third, the olives add a bit of color to the plate.
The vibrant green be sure to make yer eyes appreciate.
So, me hearties, ye should always eat pasta with olives.
The flavor, texture, and color be sure to make yer meal a success!
Human: Your response is too... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
7c1ea3c5b0c1-0 | .ipynb
.pdf
BabyAGI with Tools
Contents
Install and Import Required Modules
Connect to the Vector Store
Define the Chains
Run the BabyAGI
BabyAGI with Tools#
This notebook builds on top of baby agi, but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. B... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
7c1ea3c5b0c1-1 | Task creation chain to select new tasks to add to the list
Task prioritization chain to re-prioritize tasks
Execution Chain to execute the tasks
NOTE: in this notebook, the Execution chain will now be an agent.
from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
from langchain import OpenAI, SerpAPIWrapper,... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
7c1ea3c5b0c1-2 | tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)
agent_executor = AgentExecutor.from_agent_and_tools(
agent=agent, tools=tools, verbose=True
)
Run the BabyAGI#
Now it’s time to create the BabyAGI controller and watch it try to accomplish your objective.... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
7c1ea3c5b0c1-3 | 8. Proofread and edit the report
9. Submit the report I now know the final answer
Final Answer: The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
7c1ea3c5b0c1-4 | > Entering new AgentExecutor chain...
Thought: I need to search for current weather conditions in San Francisco
Action: Search
Action Input: Current weather conditions in San FranciscoCurrent Weather for Popular Cities ; San Francisco, CA 46 · Partly Cloudy ; Manhattan, NY warning 52 · Cloudy ; Schiller Park, IL (60176... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
7c1ea3c5b0c1-5 | 9: Include relevant data sources in the report;
10: Summarize the weather report in a concise manner;
11: Include a summary of the forecasted weather conditions;
12: Include a summary of the current weather conditions;
13: Include a summary of the historical weather patterns;
14: Include a summary of the potential weat... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
7c1ea3c5b0c1-6 | 10. Proofread the report for typos and errors I now know the final answer
Final Answer: The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding j... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
080e2afb609a-0 | .ipynb
.pdf
AutoGPT example finding Winning Marathon Times
Contents
Set up tools
Set up memory
Setup model and AutoGPT
AutoGPT for Querying the Web
AutoGPT example finding Winning Marathon Times#
Implementation of https://github.com/Significant-Gravitas/Auto-GPT
With LangChain primitives (LLMs, PromptTemplates, Vecto... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
080e2afb609a-1 | finally:
os.chdir(prev_dir)
@tool
def process_csv(
csv_file_path: str, instructions: str, output_path: Optional[str] = None
) -> str:
"""Process a CSV by with pandas in a limited REPL.\
Only use this after writing data to disk as a csv file.\
Any figures must be saved to disk to be viewed by the human... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
080e2afb609a-2 | script.extract()
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
results = "\n".join(chunk for chunk in chunks if chunk)
except Exception as e:
resul... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
080e2afb609a-3 | def _run(self, url: str, question: str) -> str:
"""Useful for browsing websites and scraping the text information."""
result = browse_web_page.run(url)
docs = [Document(page_content=result, metadata={"source": url})]
web_docs = self.text_splitter.split_documents(docs)
results = [... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
080e2afb609a-4 | Setup model and AutoGPT#
Model set-up
# !pip install duckduckgo_search
web_search = DuckDuckGoSearchRun()
tools = [
web_search,
WriteFileTool(root_dir="./data"),
ReadFileTool(root_dir="./data"),
process_csv,
query_website_tool,
# HumanInputRun(), # Activate if you want the permit asking for help... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
080e2afb609a-5 | "plan": "- Use DuckDuckGo Search to find the winning Boston Marathon times\n- Generate a table with the year, name, country of origin, and times\n- Ensure there are no legal complications",
"criticism": "None",
"speak": "I will use the DuckDuckGo Search command to find the winning Boston Marathon times ... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
080e2afb609a-6 | }
}
}
{
"thoughts": {
"text": "I need to use the query_webpage command to find the information about the winning Boston Marathon times for the past 5 years.",
"reasoning": "The previous DuckDuckGo Search command did not provide specific enough results. The query_webpage command might give more a... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
080e2afb609a-7 | "criticism": "None",
"speak": "I will generate a table with the year, name, country of origin, and times for the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "write_file",
"args": {
"file_path": "boston_marathon_winners.csv",
"text"... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.