id stringlengths 14 15 | text stringlengths 17 2.72k | source stringlengths 47 115 |
|---|---|---|
97c913f10bbc-0 | 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 Neural Network Library (oneDNN... | https://python.langchain.com/docs/integrations/text_embedding/tensorflowhub |
e4d74cabbed9-0 | Xorbits inference (Xinference)
This notebook goes over how to use Xinference embeddings within LangChain
Installation
Install Xinference through PyPI:
%pip install "xinference[all]"
Deploy Xinference Locally or in a Distributed Cluster.
For local deployment, run xinference.
To deploy Xinference in a cluster, first s... | https://python.langchain.com/docs/integrations/text_embedding/xinference |
d399c2021317-0 | AwaEmbedding
This notebook explains how to use AwaEmbedding, which is included in awadb, to embedding texts in langchain.
import the library
from langchain.embeddings import AwaEmbeddings
Embedding = AwaEmbeddings()
Set embedding model
Users can use Embedding.set_model() to specify the embedding model. \ The input of ... | https://python.langchain.com/docs/integrations/text_embedding/Awa |
a3e9192e92b0-0 | 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 embeddings are the suggested approach.
Asymmetric
from l... | https://python.langchain.com/docs/integrations/text_embedding/aleph_alpha |
f379ef3004ac-0 | Bedrock Embeddings
from langchain.embeddings import BedrockEmbeddings
embeddings = BedrockEmbeddings(
credentials_profile_name="bedrock-admin", region_name="us-east-1"
)
embeddings.embed_query("This is a content of the document")
embeddings.embed_documents(["This is a content of the document", "This is another documen... | https://python.langchain.com/docs/integrations/text_embedding/bedrock |
d4b67d96b402-0 | 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://<your-endpoint.openai.a... | https://python.langchain.com/docs/integrations/text_embedding/azureopenai |
61143f54a7d7-0 | from langchain.embeddings import HuggingFaceBgeEmbeddings
model_name = "BAAI/bge-small-en"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': False}
hf = HuggingFaceBgeEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
) | https://python.langchain.com/docs/integrations/text_embedding/bge_huggingface |
2c33ec40f742-0 | Clarifai
Clarifai is an AI Platform that provides the full AI lifecycle ranging from data exploration, data labeling, model training, evaluation, and inference.
This example goes over how to use LangChain to interact with Clarifai models. Text embedding models in particular can be found here.
To use Clarifai, you must ... | https://python.langchain.com/docs/integrations/text_embedding/clarifai |
33c369a17b6d-0 | 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]) | https://python.langchain.com/docs/integrations/text_embedding/cohere |
a2da79fa1cf7-0 | DashScope
Let's load the DashScope Embedding class.
from langchain.embeddings import DashScopeEmbeddings
embeddings = DashScopeEmbeddings(
model="text-embedding-v1", dashscope_api_key="your-dashscope-api-key"
)
text = "This is a test document."
query_result = embeddings.embed_query(text)
print(query_result)
doc_results... | https://python.langchain.com/docs/integrations/text_embedding/dashscope |
fdbd0b85c70d-0 | DeepInfra
DeepInfra is a serverless inference as a service that provides access to a variety of LLMs and embeddings models. This notebook goes over how to use LangChain with DeepInfra for text embeddings.
# sign up for an account: https://deepinfra.com/login?utm_source=langchain
from getpass import getpass
DEEPINFRA_... | https://python.langchain.com/docs/integrations/text_embedding/deepinfra |
47b1fddd80a3-0 | EDEN AI
Eden AI is revolutionizing the AI landscape by uniting the best AI providers, empowering users to unlock limitless possibilities and tap into the true potential of artificial intelligence. With an all-in-one comprehensive and hassle-free platform, it allows users to deploy AI features to production lightning fa... | https://python.langchain.com/docs/integrations/text_embedding/edenai |
d5b776f340de-0 | Embaas
embaas is a fully managed NLP API service that offers features like embedding generation, document text extraction, document to embeddings and more. You can choose a variety of pre-trained models.
In this tutorial, we will show you how to use the embaas Embeddings API to generate embeddings for a given text.
Pre... | https://python.langchain.com/docs/integrations/text_embedding/embaas |
26dec45f2dda-0 | Elasticsearch
Walkthrough of how to generate embeddings using a hosted embedding model in Elasticsearch
The easiest way to instantiate the ElasticsearchEmbeddings class it either
using the from_credentials constructor if you are using Elastic Cloud
or using the from_es_connection constructor with any Elasticsearch clus... | https://python.langchain.com/docs/integrations/text_embedding/elasticsearch |
35bc92d602bf-0 | ERNIE Embedding-V1
ERNIE Embedding-V1 is a text representation model based on Baidu Wenxin's large-scale model technology, which converts text into a vector form represented by numerical values, and is used in text retrieval, information recommendation, knowledge mining and other scenarios.
from langchain.embeddings im... | https://python.langchain.com/docs/integrations/text_embedding/ernie |
9bf74edd1d5d-0 | 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"]) | https://python.langchain.com/docs/integrations/text_embedding/fake |
ab6be4cf654a-0 | Note: This is seperate from the Google PaLM integration, it exposes Vertex AI PaLM API on Google Cloud.
By default, Google Cloud does not use Customer Data to train its foundation models as part of Google Cloud`s AI/ML Privacy Commitment. More details about how Google processes data can also be found in Google's Custo... | https://python.langchain.com/docs/integrations/text_embedding/google_vertex_ai_palm |
7945cb0c6b2e-0 | 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 512
text = "This is a test document."
q... | https://python.langchain.com/docs/integrations/text_embedding/instruct_embeddings |
0fa28d126457-0 | GPT4All
GPT4All is a free-to-use, locally running, privacy-aware chatbot. There is no GPU or internet required. It features popular models and its own models such as GPT4All Falcon, Wizard, etc.
This notebook explains how to use GPT4All embeddings with LangChain.
Install GPT4All's Python Bindings
%pip install gpt4all ... | https://python.langchain.com/docs/integrations/text_embedding/gpt4all |
e485fcaa6cc5-0 | 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([text])
In the abo... | https://python.langchain.com/docs/integrations/text_embedding/jina |
40caf537653d-0 | 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]) | https://python.langchain.com/docs/integrations/text_embedding/huggingfacehub |
34581c6824fa-0 | LocalAI
Let's load the LocalAI Embedding class. In order to use the LocalAI Embedding class, you need to have the LocalAI service hosted somewhere and configure the embedding models. See the documentation at https://localai.io/basics/getting_started/index.html and https://localai.io/features/embeddings/index.html.
from... | https://python.langchain.com/docs/integrations/text_embedding/localai |
14bdc6044c39-0 | 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.embed_query(text)
doc_res... | https://python.langchain.com/docs/integrations/text_embedding/llamacpp |
132683c6bc42-0 | MiniMax
MiniMax offers an embeddings service.
This example goes over how to use LangChain to interact with MiniMax Inference for text embedding.
import os
os.environ["MINIMAX_GROUP_ID"] = "MINIMAX_GROUP_ID"
os.environ["MINIMAX_API_KEY"] = "MINIMAX_API_KEY"
from langchain.embeddings import MiniMaxEmbeddings
embeddings ... | https://python.langchain.com/docs/integrations/text_embedding/minimax |
3d1f5fe53311-0 | ModelScope
Let's load the ModelScope Embedding class.
from langchain.embeddings import ModelScopeEmbeddings
model_id = "damo/nlp_corom_sentence-embedding_english-base"
embeddings = ModelScopeEmbeddings(model_id=model_id)
text = "This is a test document."
query_result = embeddings.embed_query(text)
doc_results = embeddi... | https://python.langchain.com/docs/integrations/text_embedding/modelscope_hub |
442f69c00c01-0 | NLP Cloud
NLP Cloud is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data.
The embeddings endpoint offers the following model:
paraphrase-multilingual-mpnet-base-v2: Paraphrase Multilingual MPNet Base V2 is a very fast model based... | https://python.langchain.com/docs/integrations/text_embedding/nlp_cloud |
8e5bb27abad5-0 | MosaicML embeddings
MosaicML offers a managed inference service. You can either use a variety of open source models, or deploy your own.
This example goes over how to use LangChain to interact with MosaicML Inference for text embedding.
# sign up for an account: https://forms.mosaicml.com/demo?utm_source=langchain
fro... | https://python.langchain.com/docs/integrations/text_embedding/mosaicml |
a55d79c07c16-0 | AINetwork
AI Network is a layer 1 blockchain designed to accommodate large-scale AI models, utilizing a decentralized GPU network powered by the $AIN token, enriching AI-driven NFTs (AINFTs).
The AINetwork Toolkit is a set of tools for interacting with the AINetwork Blockchain. These tools allow you to transfer AIN, re... | https://python.langchain.com/docs/integrations/toolkits/ainetwork |
a55d79c07c16-1 | llm = ChatOpenAI(temperature=0)
agent = initialize_agent(
tools=tools,
llm=llm,
verbose=True,
agent=AgentType.OPENAI_FUNCTIONS,
)
Example Usage
Here are some examples of how you can use the agent with the AINetwork Toolkit:
Define App name to test
appName = f"langchain_demo_{address.lower()}"
Create an app in the AIN... | https://python.langchain.com/docs/integrations/toolkits/ainetwork |
a55d79c07c16-2 | {"tx_hash": "0x018846d6a9fc111edb1a2246ae2484ef05573bd2c584f3d0da155fa4b4936a9e", "result": {"gas_amount_total": {"bandwidth": {"service": 4002, "app": {"langchain_demo_0x5beb4defa2ccc274498416fd7cb34235dbc122ac": 2}}, "state": {"service": 1640}}, "gas_cost_total": 0, "func_results": {"_createApp": {"op_results": {"0":... | https://python.langchain.com/docs/integrations/toolkits/ainetwork |
a55d79c07c16-3 | > Entering new AgentExecutor chain...
Invoking: `AINvalueOps` with `{'type': 'SET', 'path': '/apps/langchain_demo_0x5beb4defa2ccc274498416fd7cb34235dbc122ac/object', 'value': {'1': 2, '34': 56}}`
{"tx_hash": "0x3d1a16d9808830088cdf4d37f90f4b1fa1242e2d5f6f983829064f45107b5279", "result": {"gas_amount_total": {"bandwi... | https://python.langchain.com/docs/integrations/toolkits/ainetwork |
a55d79c07c16-4 | {"tx_hash": "0x37d5264e580f6a217a347059a735bfa9eb5aad85ff28a95531c6dc09252664d2", "result": {"gas_amount_total": {"bandwidth": {"service": 0, "app": {"langchain_demo_0x5beb4defa2ccc274498416fd7cb34235dbc122ac": 1}}, "state": {"service": 0, "app": {"langchain_demo_0x5beb4defa2ccc274498416fd7cb34235dbc122ac": 712}}}, "ga... | https://python.langchain.com/docs/integrations/toolkits/ainetwork |
a55d79c07c16-5 | - Address: 0x5BEB4Defa2ccc274498416Fd7Cb34235DbC122Ac
- branch_owner: true
- write_function: true
- write_owner: true
- write_rule: true
> Finished chain.
The permissions for the path /apps/langchain_demo_0x5beb4defa2ccc274498416fd7cb34235dbc122ac are as follows:
- Address: 0x5BEB4Defa2ccc274498416Fd7Cb34235DbC122Ac
... | https://python.langchain.com/docs/integrations/toolkits/ainetwork |
a55d79c07c16-6 | {"tx_hash": "0xa59d15d23373bcc00e413ac8ba18cb016bb3bdd54058d62606aec688c6ad3d2e", "result": {"gas_amount_total": {"bandwidth": {"service": 3}, "state": {"service": 866}}, "gas_cost_total": 0, "func_results": {"_transfer": {"op_results": {"0": {"path": "/accounts/0x5BEB4Defa2ccc274498416Fd7Cb34235DbC122Ac/balance", "res... | https://python.langchain.com/docs/integrations/toolkits/ainetwork |
fc95ebf50f79-0 | This notebook shows how to do question answering over structured data, in this case using the AirbyteStripeLoader.
Vectorstores often have a hard time answering questions that requires computing, grouping and filtering structured data so the high level idea is to use a pandas dataframe to help with these types of quest... | https://python.langchain.com/docs/integrations/toolkits/airbyte_structured_qa |
fc584ce05db7-0 | Amadeus
This notebook walks you through connecting LangChain to the Amadeus travel information API
To use this toolkit, you will need to set up your credentials explained in the Amadeus for developers getting started overview. Once you've received a AMADEUS_CLIENT_ID and AMADEUS_CLIENT_SECRET, you can input them as env... | https://python.langchain.com/docs/integrations/toolkits/amadeus |
fc584ce05db7-1 | toolkit = AmadeusToolkit()
tools = toolkit.get_tools()
from langchain import OpenAI
from langchain.agents import initialize_agent, AgentType
llm = OpenAI(temperature=0)
agent = initialize_agent(
tools=tools,
llm=llm,
verbose=False,
agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
)
agent.run("What is the na... | https://python.langchain.com/docs/integrations/toolkits/amadeus |
fc584ce05db7-2 | )
'Dear Paul,\n\nI am writing to request that you book the earliest flight from DFW to DCA on Aug 28, 2023. The flight details are as follows:\n\nFlight 1: DFW to ATL, departing at 7:15 AM, arriving at 10:25 AM, flight number 983, carrier Delta Air Lines\nFlight 2: ATL to DCA, departing at 12:15 PM, arriving at 2:02 PM... | https://python.langchain.com/docs/integrations/toolkits/amadeus |
b240f1d180e8-0 | CSV
This notebook shows how to use agents to interact with data in CSV format. 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 - this can be bad if the LLM generated Python cod... | https://python.langchain.com/docs/integrations/toolkits/csv |
b240f1d180e8-1 | Invoking: `python_repl_ast` with `import pandas as pd
import math
# Create a dataframe
data = {'Age': [22, 38, 26, 35, 35]}
df = pd.DataFrame(data)
# Calculate the average age
average_age = df['Age'].mean()
# Calculate the square root of the average age
square_root = math.sqrt(average_age)
square_root`
5.58569601... | https://python.langchain.com/docs/integrations/toolkits/csv |
e3535b3439b4-0 | This toolkit is used to interact with the Azure Cognitive Services API to achieve some multimodal capabilities.
First, you need to set up an Azure account and create a Cognitive Services resource. You can follow the instructions here to create a resource.
Then, you need to get the endpoint, key and region of your reso... | https://python.langchain.com/docs/integrations/toolkits/azure_cognitive_services |
ca78a937604d-0 | This notebook shows how to use an agent to compare two documents.
The high level idea is we will create a question-answering chain for each document, and then use that
This type of agent allows calling multiple functions at once. This is really useful when some steps can be computed in parallel - like when asked to co... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-1 | "{'question': "What was Alphabet's revenue?"}"
[chain/start] [1:chain:AgentExecutor > 3:tool:alphabet-earnings > 4:chain:RetrievalQA] Entering Chain run with input:
{
"query": "What was Alphabet's revenue?"
}
[chain/start] [1:chain:AgentExecutor > 3:tool:alphabet-earnings > 4:chain:RetrievalQA > 5:chain:StuffDocumentsC... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-2 | "context": "Alphabet Inc.\nCONSOLIDATED STATEMENTS OF INCOME\n(In millions, except per share amounts, unaudited)\nQuarter Ended March 31,\n2022 2023\nRevenues $ 68,011 $ 69,787 \nCosts and expenses:\nCost of revenues 29,599 30,612 \nResearch and development 9,119 11,468 \nSales and marketing 5,825 6,533 \nGeneral and a... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-3 | billion, up 3% year over year, or up 6% in constant currency. We remain committed \nto delivering long-term growth and creating capacity to invest in our most compelling growth areas by re-engineering \nour cost base.”\nQ1 2023 financial highlights (unaudited)\nOur first quarter 2023 results reflect:\ni.$2.6 billion in... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-4 | number of employees\nQuarter Ended March 31,\n2022 2023\nGoogle Search & other $ 39,618 $ 40,359 \nYouTube ads 6,869 6,693 \nGoogle Network 8,174 7,496 \nGoogle advertising 54,661 54,548 \nGoogle other 6,811 7,413 \nGoogle Services total 61,472 61,961 \nGoogle Cloud 5,821 7,454 \nOther Bets 440 288 \nHedging gains (los... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-5 | 191 \nOther Bets (835) (1,225) \nCorporate costs, unallocated(1) (338) (3,288) \nTotal income from operations $ 20,094 $ 17,415 \n(1)Hedging gains (losses) related to revenue included in unallocated corporate costs were $278 million and $84 million for the \nthree months ended March 31, 2022 and 2023 , respectively. Fo... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-6 | Revenues \nfrom Other Bets are generated primarily from the sale of health technology and internet services.\nAfter the segment reporting changes discussed above, unallocated corporate costs primarily include AI-focused \nshared R&D activities; corporate initiatives such as our philanthropic activities; and corporate s... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-7 | }
[llm/start] [1:chain:AgentExecutor > 3:tool:alphabet-earnings > 4:chain:RetrievalQA > 5:chain:StuffDocumentsChain > 6:chain:LLMChain > 7:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [ | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-8 | "System: Use the following pieces of context to answer the users question. \nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\nAlphabet Inc.\nCONSOLIDATED STATEMENTS OF INCOME\n(In millions, except per share amounts, unaudited)\nQuarter Ended March 31,\n2022 ... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-9 | our long track record of innovation.”\nRuth Porat, CFO of Alphabet and Google, said: “Resilience in Search and momentum in Cloud resulted in Q1 \nconsolidated revenues of $69.8 billion, up 3% year over year, or up 6% in constant currency. We remain committed \nto delivering long-term growth and creating capacity to inv... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-10 | currency revenues” for \nmore details.\n\nQ1 2023 supplemental information (in millions, except for number of employees; unaudited)\nRevenues, T raffic Acquisition Costs (TAC), and number of employees\nQuarter Ended March 31,\n2022 2023\nGoogle Search & other $ 39,618 $ 40,359 \nYouTube ads 6,869 6,693 \nGoogle Network... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-11 | in the second quarter of \n2023.\nQuarter Ended March 31,\n2022 2023\n(recast)\nOperating income (loss):\nGoogle Services $ 21,973 $ 21,737 \nGoogle Cloud (706) 191 \nOther Bets (835) (1,225) \nCorporate costs, unallocated(1) (338) (3,288) \nTotal income from operations $ 20,094 $ 17,415 \n(1)Hedging gains (losses) rel... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-12 | and other services for \nenterprise customers. Google Cloud generates revenues from fees received for Google Cloud Platform \nservices, Google Workspace communication and collaboration tools, and other enterprise services.\n•Other Bets is a combination of multiple operating segments that are not individually material. ... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-13 | ]
}
[llm/end] [1:chain:AgentExecutor > 3:tool:alphabet-earnings > 4:chain:RetrievalQA > 5:chain:StuffDocumentsChain > 6:chain:LLMChain > 7:llm:ChatOpenAI] [1.61s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "Alphabet's revenue for the quarter ended March 31, 2023, was $69,787 million.",
"generation_info... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-14 | {
"result": "Alphabet's revenue for the quarter ended March 31, 2023, was $69,787 million."
}
[tool/end] [1:chain:AgentExecutor > 3:tool:alphabet-earnings] [1.86s] Exiting Tool run with output:
"{'query': "What was Alphabet's revenue?", 'result': "Alphabet's revenue for the quarter ended March 31, 2023, was $69,787 mil... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-15 | "context": "S U M M A R Y H I G H L I G H T S \n(1) Excludes SBC (stock -based compensation).\n(2) Free cash flow = operating cash flow less capex.\n(3) Includes cash, cash equivalents and investments.Profitability 11.4% operating margin in Q1\n$2.7B GAAP operating income in Q1\n$2.5B GAAP net income in Q1\n$2.9B non -... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-16 | in our cash and investments3in Q1 to $22.4B\nOperations Cybertruck factory tooling on track; producing Alpha versions\nModel Y was the best -selling vehicle in Europe in Q1\nModel Y was the best -selling vehicle in the US in Q1 (ex -pickups)\n\n01234O T H E R H I G H L I G H T S\n9Services & Other gross margin\nEnergy ... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-17 | 564 \nTotal automotive revenues 16,861 14,602 18,692 21,307 19,963 \nEnergy generation and storage 616 866 1,117 1,310 1,529 \nServices and other 1,279 1,466 1,645 1,701 1,837 \nTotal revenues 18,756 16,934 21,454 24,318 23,329 \nCOST OF REVENUES\nAutomotive sales 10,914 10,153 13,099 15,433 15,422 \nAutomotive leasing... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-18 | INCOME 3,280 2,269 3,331 3,707 2,539 \nNet (loss) income attributable to noncontrolling interests and redeemable noncontrolling interests in \nsubsidiaries(38) 10 39 20 26 \nNET INCOME ATTRIBUTABLE TO COMMON STOCKHOLDERS 3,318 2,259 3,292 3,687 2,513 \nNet income per share of common stock attributable to common stockho... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-19 | 405,278 422,875 36%\nof which subject to operating lease accounting 12,167 9,227 11,004 15,184 22,357 84%\nTotal end of quarter operating lease vehicle count 128,402 131,756 135,054 140,667 153,988 20%\nGlobal vehicle inventory (days of supply )(1)3 4 8 13 15 400%\nSolar deployed (MW) 48 106 94 100 67 40%\nStorage depl... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-20 | }
[llm/start] [1:chain:AgentExecutor > 8:tool:tesla-earnings > 9:chain:RetrievalQA > 10:chain:StuffDocumentsChain > 11:chain:LLMChain > 12:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [ | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-21 | "System: Use the following pieces of context to answer the users question. \nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\nS U M M A R Y H I G H L I G H T S \n(1) Excludes SBC (stock -based compensation).\n(2) Free cash flow = operating cash flow less cap... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-22 | to ensure we lay a proper foundation for the best \npossible future.Cash Operating cash flow of $2.5B\nFree cash flow2of $0.4B in Q1\n$0.2B increase in our cash and investments3in Q1 to $22.4B\nOperations Cybertruck factory tooling on track; producing Alpha versions\nModel Y was the best -selling vehicle in Europe in Q... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-23 | 15,514 13,670 17,785 20,241 18,878 \nAutomotive regulatory credits 679 344 286 467 521 \nAutomotive leasing 668 588 621 599 564 \nTotal automotive revenues 16,861 14,602 18,692 21,307 19,963 \nEnergy generation and storage 616 866 1,117 1,310 1,529 \nServices and other 1,279 1,466 1,645 1,701 1,837 \nTotal revenues 18,... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-24 | (48)\nINCOME BEFORE INCOME TAXES 3,626 2,474 3,636 3,983 2,800 \nProvision for income taxes 346 205 305 276 261 \nNET INCOME 3,280 2,269 3,331 3,707 2,539 \nNet (loss) income attributable to noncontrolling interests and redeemable noncontrolling interests in \nsubsidiaries(38) 10 39 20 26 \nNET INCOME ATTRIBUTABLE TO C... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-25 | 10,695 -27%\nModel 3/Y deliveries 295,324 238,533 325,158 388,131 412,180 40%\nTotal deliveries 310,048 254,695 343,830 405,278 422,875 36%\nof which subject to operating lease accounting 12,167 9,227 11,004 15,184 22,357 84%\nTotal end of quarter operating lease vehicle count 128,402 131,756 135,054 140,667 153,988 20... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-26 | ]
}
[llm/end] [1:chain:AgentExecutor > 8:tool:tesla-earnings > 9:chain:RetrievalQA > 10:chain:StuffDocumentsChain > 11:chain:LLMChain > 12:llm:ChatOpenAI] [1.17s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "Tesla's revenue for Q1-2023 was $23.329 billion.",
"generation_info": null,
"message": {
"conten... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-27 | }
[tool/end] [1:chain:AgentExecutor > 8:tool:tesla-earnings] [1.61s] Exiting Tool run with output:
"{'query': "What was Tesla's revenue?", 'result': "Tesla's revenue for Q1-2023 was $23.329 billion."}"
[llm/start] [1:chain:AgentExecutor > 13:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-28 | {
"generations": [
[
{
"text": "Alphabet had a revenue of $69,787 million, while Tesla had a revenue of $23.329 billion. Therefore, Alphabet had more revenue than Tesla.",
"generation_info": null,
"message": {
"content": "Alphabet had a revenue of $69,787 million, while Tesla had a revenue of $23.329 billion. Therefore... | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
ca78a937604d-29 | {'input': 'did alphabet or tesla have more revenue?',
'output': 'Alphabet had a revenue of $69,787 million, while Tesla had a revenue of $23.329 billion. Therefore, Alphabet had more revenue than Tesla.'} | https://python.langchain.com/docs/integrations/toolkits/document_comparison_toolkit |
4bdf9c375d0e-0 | Github
The Github toolkit contains tools that enable an LLM agent to interact with a github repository. The tool is a wrapper for the PyGitHub library.
Quickstart
Install the pygithub library
Create a Github app
Set your environmental variables
Pass the tools to your agent with toolkit.get_tools()
Each of these steps... | https://python.langchain.com/docs/integrations/toolkits/github |
4bdf9c375d0e-1 | from langchain.llms import OpenAI
from langchain.utilities.github import GitHubAPIWrapper
# Set your environment variables using os.environ
os.environ["GITHUB_APP_ID"] = "123456"
os.environ["GITHUB_APP_PRIVATE_KEY"] = "path/to/your/private-key.pem"
os.environ["GITHUB_REPOSITORY"] = "username/repo-name"
os.environ["GITH... | https://python.langchain.com/docs/integrations/toolkits/github |
4bdf9c375d0e-2 | # This example also requires an OpenAI API key
os.environ["OPENAI_API_KEY"] = ""
llm = OpenAI(temperature=0)
github = GitHubAPIWrapper()
toolkit = GitHubToolkit.from_github_api_wrapper(github)
agent = initialize_agent(
toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)
agent.run(
"You... | https://python.langchain.com/docs/integrations/toolkits/github |
4bdf9c375d0e-3 | > Finished chain.
'The README.md file has been updated with the new content.'
Example: Advanced Agent
If your agent does not need to use all 8 tools, you can build tools individually to use. For this example, we'll make an agent that does not use the create_file, delete_file or create_pull_request tools, but can ... | https://python.langchain.com/docs/integrations/toolkits/github |
4bdf9c375d0e-4 | Action: Search
Action Input: "most popular frontend framework"
Observation: Alex Ivanovs February 25, 2023 Table of Contents What are the current Front-end trends? Top Front-end Frameworks for 2023 #1 - React #2 - Angular #3 - Vue #4 - Svelte #5 - Preact #6 - Ember #7 - Solid #8 - Lit #9 - Alpine #10 - Stencil #11 - Qw... | https://python.langchain.com/docs/integrations/toolkits/github |
4bdf9c375d0e-5 | Observation: File content was not updated because old content was not found.It may be helpful to use the read_file action to get the current file contents.
Thought:I need to first read the contents of the README.md file to get the current content. Then I can update the file with the new content.
Action: Read File
Acti... | https://python.langchain.com/docs/integrations/toolkits/github |
9b863592c3b4-0 | This notebook walks through connecting a LangChain email to the Gmail API.
To use this toolkit, you will need to set up your credentials explained in the Gmail API docs. Once you've downloaded the credentials.json file, you can start using the Gmail API. Once this is done, we'll install the required libraries.
By defau... | https://python.langchain.com/docs/integrations/toolkits/gmail |
9b863592c3b4-1 | # Can review scopes here https://developers.google.com/gmail/api/auth/scopes
# For instance, readonly scope is 'https://www.googleapis.com/auth/gmail.readonly'
credentials = get_gmail_credentials(
token_file="token.json",
scopes=["https://mail.google.com/"],
client_secrets_file="credentials.json",
)
api_resource = buil... | https://python.langchain.com/docs/integrations/toolkits/gmail |
9b863592c3b4-2 | GmailGetThread(name='get_gmail_thread', description=('Use this tool to search for email messages. The input must be a valid Gmail query. The output is a JSON list of messages.',), args_schema=<class 'langchain.tools.gmail.get_thread.GetThreadSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager... | https://python.langchain.com/docs/integrations/toolkits/gmail |
3b29ccec690d-0 | Google Drive tool
This notebook walks through connecting a LangChain to the Google Drive API.
Prerequisites
Create a Google Cloud project or use an existing project
Enable the Google Drive API
Authorize credentials for desktop app
pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib... | https://python.langchain.com/docs/integrations/toolkits/google_drive |
3b29ccec690d-1 | application/vnd.google-apps.spreadsheet (GSheet)
application/vnd.google.colaboratory (Notebook colab)
application/vnd.openxmlformats-officedocument.presentationml.presentation (PPTX)
application/vnd.openxmlformats-officedocument.wordprocessingml.document (DOCX)
It's possible to update or customize this. See the documen... | https://python.langchain.com/docs/integrations/toolkits/google_drive |
3b29ccec690d-2 | # By default, search only in the filename.
tool = GoogleDriveSearchTool(
api_wrapper=GoogleDriveAPIWrapper(
folder_id=folder_id,
num_results=2,
template="gdrive-query-in-folder", # Search in the body of documents
)
)
import logging
logging.basicConfig(level=logging.INFO)
tool.run("machine learning")
from langchain.agen... | https://python.langchain.com/docs/integrations/toolkits/google_drive |
21e1e9a99892-0 | Jira
This notebook goes over how to use the Jira toolkit.
The Jira toolkit 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/jira.html
To us... | https://python.langchain.com/docs/integrations/toolkits/jira |
65ef8c23475c-0 | This notebook showcases an agent interacting with large JSON/dict objects. This is useful when you want to answer questions about a JSON blob that's too large to fit in the context window of an LLM. The agent is able to iteratively explore the blob to find what it needs to answer the user's question.
In the below examp... | https://python.langchain.com/docs/integrations/toolkits/json |
65ef8c23475c-1 | > Entering new AgentExecutor chain...
Action: json_spec_list_keys
Action Input: data
Observation: ['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']
Thought: I should look at the paths key to see what endpoints exist
Action: json_spec_list_keys
Action Input: data["paths"]
Observation: ['/engines... | https://python.langchain.com/docs/integrations/toolkits/json |
65ef8c23475c-2 | Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"]["content"]["application/json"]
Observation: ['schema']
Thought: I should look at the schema key to see what parameters are required
Action: json_spec_list_keys
Action Input: data["paths"]["/completions"]["post"]["requestBody"... | https://python.langchain.com/docs/integrations/toolkits/json |
65ef8c23475c-3 | > Finished chain.
"The required parameters in the request body to the /completions endpoint are 'model'." | https://python.langchain.com/docs/integrations/toolkits/json |
0e2fd142f99c-0 | MultiOn
This notebook walks you through connecting LangChain to the MultiOn Client in your browser
To use this toolkit, you will need to add MultiOn Extension to your browser as explained in the MultiOn for Chrome.
pip install --upgrade multion langchain -q
from langchain.agents.agent_toolkits import MultionToolkit
imp... | https://python.langchain.com/docs/integrations/toolkits/multion |
18858094916d-0 | This notebook walks through connecting LangChain to Office365 email and calendar.
To use this toolkit, you will need to set up your credentials explained in the Microsoft Graph authentication and authorization overview. Once you've received a CLIENT_ID and CLIENT_SECRET, you can input them as environmental variables be... | https://python.langchain.com/docs/integrations/toolkits/office365 |
18858094916d-1 | O365SearchEmails(name='messages_search', description='Use this tool to search for email messages. The input must be a valid Microsoft Graph v1.0 $search query. The output is a JSON list of the requested resource.', args_schema=<class 'langchain.tools.office365.messages_search.SearchEmailsInput'>, return_direct=False, v... | https://python.langchain.com/docs/integrations/toolkits/office365 |
f4cec29c55a4-0 | Natural Language API Toolkits (NLAToolkits) permit LangChain Agents to efficiently plan and combine calls across endpoints.
This notebook demonstrates a sample composition of the Speak, Klarna, and Spoonacluar APIs.
For a detailed walkthrough of the OpenAPI chains wrapped within the NLAToolkit, see the OpenAPI Operati... | https://python.langchain.com/docs/integrations/toolkits/openapi_nla |
f4cec29c55a4-1 | > Entering new AgentExecutor chain...
I need to find a recipe and an outfit that is Italian-themed.
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 ... | https://python.langchain.com/docs/integrations/toolkits/openapi_nla |
f4cec29c55a4-2 | > 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 ... | https://python.langchain.com/docs/integrations/toolkits/openapi_nla |
4bf4e892bacb-0 | We can construct agents to consume arbitrary APIs, here APIs conformant to the OpenAPI/Swagger specification.
In this example, we'll consider an approach called hierarchical planning, common in robotics and appearing in recent works for LLMs X robotics. We'll see it's a viable approach to start working with a massive A... | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-1 | > Entering new AgentExecutor chain...
Action: requests_get
Action Input: {"url": "https://api.spotify.com/v1/me", "output_instructions": "Extract the user's id and username"}
Observation: ID: 22rhrz4m4kvpxlsb5hezokzwi, Username: Jeremy Welborn
Thought:Action: requests_get
Action Input: {"url": "https://api.spotify.com/... | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-2 | Action: requests_get
Action Input: {"url": "https://api.spotify.com/v1/recommendations?seed_genres=blues", "output_instructions": "Extract the list of recommended tracks with their ids and names"}
Observation: [
{
id: '03lXHmokj9qsXspNsPoirR',
name: 'Get Away Jordan'
}
]
Thought:I am finished executing the plan.
Final ... | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-3 | > Entering new AgentExecutor chain...
Action: requests_get
Action Input: {"url": "https://api.openai.com/v1/engines", "output_instructions": "Extract the ids of the engines"}
Observation: babbage, davinci, text-davinci-edit-001, babbage-code-search-code, text-similarity-babbage-001, code-davinci-edit-001, text-davinci-... | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-4 | > Finished chain.
Observation: I need more information on how to provide the model parameter correctly in the POST request to generate a short piece of advice.
Thought:I need to adjust my plan to include the model parameter in the POST request.
Action: api_planner
Action Input: I need to find the right API calls to ge... | https://python.langchain.com/docs/integrations/toolkits/openapi |
4bf4e892bacb-5 | > Finished chain.
Observation: The generated text is not a piece of advice on improving communication skills. I would need to retry the API call with a different prompt or model to get a more relevant response.
Thought:I need to adjust my plan to include a more specific prompt for generating a short piece of advice on... | https://python.langchain.com/docs/integrations/toolkits/openapi |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.