pathway.com Open in urlscan Pro
13.38.210.9  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Go back
FeaturesPricingArchitecture Request a Demo


SAVE TIME AND MANAGE CONTRACT RISK
WITH AI

Get Simplified Generative AI-powered Insights for All Your Contracts in G-Drive
and Sharepoint

Request a Demo


--------------------------------------------------------------------------------


REFERENCE ARCHITECTURE




WE'RE TRUSTED BY



--------------------------------------------------------------------------------


HOW IT HELPS

To understand obligations

Automatically scan contracts to extract due dates, renewal triggers, payment
terms and enable workflow to ensure compliance and timely action. Alert
appropriate parties as regulatory environment changes or key deadlines approach.


To assess your liabilities

Scan for risky clauses, provide risk scoring, and flag potential issues.
Highlight areas that need review by legal or business teams.


To negotiate better

During renewal and contract negotiations, provide comparative data, flag
unacceptable/risky terms and suggest alternative based on past deals and group
norms.



--------------------------------------------------------------------------------

As a lawyer, I’m always reviewing contracts as part of audits and due diligence
processes. Now I can instantly search our entire contract repository stored in
Sharepoint and identify specific clauses, terms, and obligations. It saves me
tons of time and allows me to focus on the most strategic or risky contracts

Corporate Lawyer, a Fortune 500 company

--------------------------------------------------------------------------------


PROVEN BUSINESS IMPACT

*The Business Impact has been calculated on a company with a team of 30
counsels, that should be recruiting 5 additional counsels to handle the growing
demand. The business impact is accounted for the number of business days in a
year.

Productivity savings# of UnitsCost per UnitAnnualCounsel
FTEs5$95,000$475,000Cost savings# of UnitsCost per UnitAnnualSavings from other
external SaaS services30$3,6000$108,000Business Impact# of UnitsCost per
UnitAnnualImproved quality of service for non Legal users251$1,500$376,500Faster
answers to non Legal users251$20$5,020Improved contract drafting
workflow251$160$40,160C-Suite dashboard overview of global contractual
landscape20$8,000$160,000Automatic evaluation of impact of new regulations
(CPRA, GDPR, LGPD,...)10$5,000$50,000Sub-total$631,680Total annual impact &
savings$1,214,680Compute your ROI with us

Backed by Enterprise Security & Authentication
 * Host on your cloud or on-premise
 * Secure by Design
 * Granular Access Management
 * Compliance-Ready

Let's talk

--------------------------------------------------------------------------------


PRICING

Up to 5 GB
$100/ month
Up to 25 GB
$400/ month
> 25 GBReachout for pricing

--------------------------------------------------------------------------------


TRY IT OUT


INTERACT WITH DEMO PIPELINES

Browse files
Try Q&A on Contract Documents
Test the REST endpoint for developers


PATHWAY-GENERATED OPENAPI DESCRIPTION

 1.0.0 

OAS 3.0

https://demo-rag-question-answering.pathway.stream/_schema

Servers
https://demo-rag-question-answering.pathway.stream



DOCUMENT QUESTION ANSWERING

POST
/v1/pw_ai_aggregate_responses
Aggregate and categorize responses for a question between different files.


Aggregate and categorize responses for a given question between different files.
Given list of responses from different files, creates executive summary in a
short format.

Answer will be text with separated sections to summarize files.

The openai_api_key is API key is used only for this query and not stored on
server.

PARAMETERS

Cancel

No parameters

REQUEST BODY

application/json
Examples: Aggregate and summarize different files around a question.Aggregate
and summarize different files around a question with GPT-4 model.
{ "question": "Is there any action required from the marketing team?",
"answers": [ "File a.pdf - We need approval for social media campaign from
marketing dept.", "File b.pdf - There are no action points.", "Budget approval
is needed from head of marketing." ], "openai_api_key": "sk-..." }

Execute

RESPONSES

CodeDescriptionLinks200

OK

No links400

The request is incorrect. Please check if it complies with the auto-generated
and Pathway input table schemas

No links

POST
/v1/pw_ai_answer
Answer questions about your files with GPT.


Chat with your files from Drive, Sharepoint and many more with GPT! Pathway
automatically searches for relevant parts of your documents and GPT responds
with up-to-date answers for your questions.

filters defaults to null which means no document will be retrieved.

Any JMESPath filter can be sent to answer the question based on the docs.

model defaults to gpt-3.5-turbo if left as null, can be set to gpt-4 or any
other OpenAI model.

response_type can be either short or long. Short gives a very concise answer
without explanation where as long gives detailed answer.

The openai_api_key is API key is used only for this query and not stored on
server.

PARAMETERS

Cancel

No parameters

REQUEST BODY

application/json
Examples: Basic document question answering.Basic document question answering
with all files included for search.Basic chat with GPT without context.Document
question answering with GPT-4.Document question answering with detailed
responses.
{ "prompt": "What is the start date of the contract?", "filters":
"contains(path, `Ide`)", "openai_api_key": "sk-..." }

Execute

RESPONSES

CodeDescriptionLinks200

OK

No links400

The request is incorrect. Please check if it complies with the auto-generated
and Pathway input table schemas

No links

POST
/v1/pw_ai_summary
Endpoint for summarizing text(s) with GPT.


Creates a summary while preserving important details and entities with GPT.

model defaults to gpt-3.5-turbo, can be set to different model.

text_list is list of strings to be summarized.

PARAMETERS

Cancel

No parameters

REQUEST BODY

application/json
Examples: Default (default model)Use GPT-4 for summary.
{ "text_list": [ "I love apples.", "I love oranges." ], "openai_api_key":
"sk-..." }

Execute

RESPONSES

CodeDescriptionLinks200

OK

No links400

The request is incorrect. Please check if it complies with the auto-generated
and Pathway input table schemas

No links


DOCUMENT INDEXING

POST
/v1/pw_list_documents
Get list of input documents.


Get list of input documents and their metadata as list of dictionaries. If no
filter is provided, all input documents are retrieved.

PARAMETERS

Cancel

No parameters

REQUEST BODY

application/json
Examples: Default (no filters)Only list files beginning with fooOnly list pdf
filesOnly list pdf files that have the word `report` in name
{}

Execute

RESPONSES

CodeDescriptionLinks200

OK

No links400

The request is incorrect. Please check if it complies with the auto-generated
and Pathway input table schemas

No links

POST
/v1/retrieve
Do a similarity search for your query


Request the given number of documents from the realtime-maintained index

PARAMETERS

Cancel

No parameters

REQUEST BODY

application/json
{ "query": "Pathway data processing framework", "k": 2, "metadata_filter": null,
"filepath_globpattern": null }
Execute

RESPONSES

CodeDescriptionLinks200

OK

No links400

The request is incorrect. Please check if it complies with the auto-generated
and Pathway input table schemas

No links

POST
/v1/statistics
Get current indexer stats


Request for the basic stats of the indexer process. It returns the number of
documents that are currently present in the indexer and the time the last of
them was added.

PARAMETERS

Cancel

No parameters

REQUEST BODY

application/json
{}
Execute

RESPONSES

CodeDescriptionLinks200

OK

No links400

The request is incorrect. Please check if it complies with the auto-generated
and Pathway input table schemas

No links



Learn how this pipeline works

Pathway utilizes RAG (Retrieval-Augmented Generation) to power its document AI
magic. Here's a breakdown of the pipeline:

1. Document Ingestion:
Connect your document sources like Google Drive, SharePoint, local storage, or
S3.
Supported formats include text, PDF, DOCX, and HTML.
Documents are NOT duplicated and indexed for efficient retrieval.


2. Retrieval Stage:
When you ask a question, Pathway searches its document index using powerful
algorithms.
Relevant passages are retrieved based on their potential to answer your query.


3. Generation Stage:
The retrieved passages are fed into a GPT model of choice, fine-tuned for
document understanding.
GPT model synthesizes the information and generates a clear, concise, and
informative answer to your question.


4. Summarization (Optional):
For multiple documents, Pathway can automatically summarize responses,
presenting key points for quick review.


5. Continuous Learning:
Pathway constantly learns and adapts. As your documents change, the retrieval
and generation models get updated through an always refreshed vector index,
ensuring your answers are always based on the latest information.


Benefits:
Accurate & Insightful Answers: Get straight to the point with answers sourced
directly from your documents.
Effortless Maintenance: No separate data preprocessing needed. No need for a
separate vector database. Pathway automatically keeps itself up-to-date.
Highly Customizable: Adapt the pipeline to your specific needs, including
prompts, search queries, and more.
Seamless Integration: Works with various document sources and integrates
smoothly with your existing workflows.


See the source code
 * 
 * 
 * 

Company
 * Features
 * Success Stories
 * Our Story
 * Careers
 * Events

Developers
 * Documentation
 * Showcases
 * Compare Stream Processing Frameworks
 * Pathway vs Flink
 * Pathway vs Kafka Streams
 * Pathway vs Spark Streaming

About
 * Legal & GDPR
 * Equal opportunity employer
 * Privacy policy
 * Licensing
 * Media kit
 * Glossary

Contact
 * Let's talk
 * Chat with us on Discord
 * Pathway
 * 96bis Boulevard Raspail
 * Agoranov
 * 75006 Paris, France

© 2021-2024 Pathway
SearchK