Mar 25, 2023 · LangChain is a powerful Python library that provides a standard interface through which you can interact with a variety of LLMs and integrate them with your applications and custom data. Using GPT-3 and LangChain's question_answering to query these documents. There are two main methods an output parser must implement: "Get format instructions": A method. This module is aimed at making this easy. base import BasePromptTemplate from. com/signupLangChain Cookbook: https://github. They’re lightweight, affordable, and easy to use. ArgumentParser(description=__doc__) parser. What is Langchain? In simple terms, langchain is a framework and library of useful templates and tools that make it easier to build large language model applications that use custom data and external tools. This documentation is organized into four sections (according to the Diátaxis documentation framework ). Creation: 21 Feb 2023 @. The Memory does exactly that. Extracting Text from PDFs using Node. Pinecone is a vectorstore for storing embeddings and your PDF in text to later retrieve. They may look old-fashioned, but they are durable and versatile Expert Advice On Improving Your Home Videos Latest View All Guides Latest View All Radi. Its primary. base import BasePromptTemplate from. As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of updating code, better documentation, or project to feature. Table of Contents. I've been using the Langchain library, UnstructuredFileLoader from langchain. Unstructured currently supports loading of text files, powerpoints, html, pdfs, images, and more. This tutorial walks through a simple example of crawling a website (in this example, the OpenAI website), turning the crawled pages into embeddings using the Embeddings API, and then creating a basic search functionality that allows a user to ask questions about the embedded information. You can build a ChatPromptTemplate from one or more MessagePromptTemplates. Tools are functions or pydantic classes agents can use to connect with the outside world. How to Talk to a PDF using LangChain and ChatGPT by Automata Learning Lab. In this video, I give an overview of Structured Output parsers with Langchain and discuss some of their use cases. Which is then parsed using a parser to check the validity of the code that is if it is executable. Open Source LLMs. Replace the OpenAI LLM component with the HuggingFace Inference Wrapper for HuggingFace LLMs. Here’s what you need to know. How Can You Run LangChain Queries? One of the primary uses for LangChain is to query some text data. Source code for langchain. High Level Walkthrough At a high level, there are two components to setting up ChatGPT over your own data: (1) ingestion of the data, (2) chatbot over the data. This adaptability makes LangChain ideal for constructing AI applications across various scenarios and sectors. At its barebones, LangChain provides an abstraction of all the different types of LLM services, combines. run, description = "useful for. """ from __future__ import annotations from typing import Any, Dict, List. from langchain. The framework, however, introduces additional possibilities, for example, the one of easily using external data sources, such as Wikipedia, to amplify the capabilities provided by. Subclasses should generally not over-ride this parse method. Picking up a LLM Using LangChain will usually require integrations with one or more model providers, data stores, apis, etc. LangChain Expression Language makes it easy to create custom chains. Chat Messages. from langchain. The first step in doing this is to load the data into documents (i. The OpenAI Cookbook shares example code for accomplishing common tasks with the OpenAI API. One of the many interesting features. In this course you will learn and get experience with the following topics: Models, Prompts and Parsers: calling LLMs, providing prompts and parsing the. A class that extends the AgentActionOutputParser to parse the output of the ChatAgent in LangChain. parser=parser, llm=OpenAI(temperature=0). transform ( generator: AsyncGenerator < ChainValues, any, unknown >, options: Partial < BaseCallbackConfig > ): AsyncGenerator < ChainValues. Creating the map prompt and chain. """ default_destination: str = "DEFAULT" next. output_parsers import RetryWithErrorOutputParser. For example, to create a bot that can translate from English to French:. As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of updating code, better documentation, or project to feature. You can speed up the scraping process by scraping and parsing multiple urls concurrently. The input/output for LLMs is simple and easy to understand - a string. Values are the attribute values, which will be serialized. It first combines the chat history (either explicitly passed in or retrieved from the provided memory) and the question into a standalone question, then looks up relevant documents from the retriever, and finally. 1 and <4. LangChain offers several types of output parsers. May 22, 2023 · Those are LangChain’s signature emojis. These LLMs are specifically designed to handle unstructured text data and. It offers a suite of features for artificial general intelligence, including Model I. You can do this in the terminal by running: mkdir quote-scraper. lc_attributes (): undefined | SerializedFields. (template = output_parser. In this video, I will show you how to interact with your data using LangChain without the need for OpenAI apis, for absolutely free. Now, I'm attempting to use the extracted data as input for ChatGPT by utilizing the OpenAIEmbeddings. Jun 7, 2023 · Published on June 7, 2023. from langchain. "Parse": A method which takes in a string (assumed to be the response. Resources and ideas to put mod. Below are links to tutorials and courses on LangChain. You’ll begin your journey by learning how to install and set up LangChain, ensuring you have the most up-to-date version. This tutorial provides an overview of what you can do with LangChain, including the problems that LangChain solves and examples of data use cases. The most commonly used type of chain is an LLMChain, which combines a PromptTemplate, a Model, and Guardrails to take user input, format it accordingly, pass it to the model. Picking up a LLM Using LangChain will usually require integrations with one or more model providers, data stores, apis, etc. Class that represents a chat prompt. document_loaders to successfully extract data from a PDF document. A primary driver of a lot of these transformers is the Unstructured python package. LangChain supports various popular LLM architectures, such as GPT-3, enabling developers to work with state-of-the-art models for their applications. It's offered in Python or JavaScript (TypeScript) packages. Here’s another parser strictly less powerful than Pydantic/JSON parsing. LangChain has become a tremendously popular toolkit for building a wide range of LLM-powered applications, including chat, Q&A and document search. OutputParserException | 🦜️🔗 Langchain. """ parser: BaseOutputParser [T] retry_chain: LLMChain. base import BasePromptTemplate from. Design# Prepare data: Upload all python project files using the langchain. schema import Document from pydantic import BaseModel. Unstructured File. Step 4: Generate embeddings. prepare_inputs_for_autoembed (inputs) go over all the inputs and if something is either wrapped in _ToSelectFrom or _BasedOn, and if their inner values are not already _Embed, then wrap them in EmbedAndKeep while retaining their _ToSelectFrom or _BasedOn status. For example, LangChain supports some end-to-end chains (such as AnalyzeDocumentChain for summarization, QnA, etc) and some specific ones (such as GraphQnAChain for creating, querying, and saving graphs). So, in a way, Langchain provides a way for feeding LLMs with new data that it has not been trained on. Overrides ListOutputParser. Scrimba is a code-learning platform that allows you to interactively edit and run code while watching a video walkthrough. You switched accounts on another tab or window. Next, display the app’s title “🦜🔗 Quickstart App” using the st. Specify the schema of what should be extracted and provide some examples. This example demonstrates the use of the SQLDatabaseChain for answering questions over a database. If you're looking to harness the power of large language models for your data, this is the video for you. "Parse": A method which takes in a string (assumed to be the response from a language model) and parses it into some structure. Adding Message Memory backed by a database to an Agent. Unfortunately, out of the box, langchain does not automatically handle these "failed to parse errors when the output isn't formatted right" errors. Getting Started; Generic Functionality. DateTime parser — Parses a datetime string into a Python datetime object. This notebook showcases an agent designed to interact with a sql databases. Install Chroma with: pip install chromadb. In the OpenAI family, DaVinci can do reliably but Curie's ability. as_retriever() ) # Set. A well-designed letterhead not only adds a touch of professionalism to your correspondence but also helps to establish your brand id. class Joke (BaseModel): setup: str = Field (description="question to set up a joke") punchline: str = Field (description="answer to resolve the joke") # You can add. The nice thing is that LangChain provides SDK to integrate with many LLMs provider, including Azure OpenAI. OpenAI is a type of LLM (provider) that you can use but there are others like Cohere, Bloom, Huggingface, etc. Values are the attribute values, which will be serialized. Output parsers are responsible for instructing the LLM to respond in a specific format. Create embeddings from this text. Installation # To get started, install. 🦜🔗 LangChain. Installing LangChain Before installing the langchain package, ensure you have a Python version of ≥ 3. chat_models import ChatOpenAI chat = ChatOpenAI(temperature=0. The standard interface that LangChain provides has two methods: predict: Takes in a string, returns a string; predictMessages: Takes in a list of messages, returns a message. Output Parsers# pydantic model langchain. LangChain has become the go-to tool for AI developers worldwide to build generative AI applications. LangChain makes it easy to manage interactions with language models. This framework was created recently and is already used as the industry standard for building tools powered by LLMs. I should look up the current weather Action: SearX Search Action Input: "weather in Pomfret" Observation: Mainly cloudy with snow showers around in the morning. A map of additional attributes to merge with constructor args. Click “Reset password”. These are designed to be modular and useful regardless of how they are used. Default implementation of abatch, which calls ainvoke N times. (Chains can be built of entities other than LLMs but for now, let’s stick with this definition for simplicity). ChatPromptTemplate<RunInput, PartialVariableName. tools import BaseTool from langchain. pdf-parse for pdf extraction. With just a few clicks, you can have the forms you need right at your fingertips. How Can You Run LangChain Queries? One of the primary uses for LangChain is to query some text data. The construction of the chain is a bit different so please be careful when you use gpt-3. load () Load text from the url (s) in web_path. Read how to migrate your code here. As you may know, GPT models have been trained on data up until 2021, which can be a significant limitation. In our previous guide on Getting Started with LangChain, we discussed how the library is filling in many of the missing pieces when it comes to building more advanced large language model (LLM) applications. from langchain. The input/output for LLMs is simple and easy to understand - a string. Specifically, this means all objects (prompts, LLMs, chains, etc) are designed in a way where they can be serialized and shared between languages. Agentic: allow a language model to interact with its environment. LangChain provides a framework on top of several APIs for LLMs. Are you interested in learning the art of quilting? Look no further than Jenny Doan’s quilting tutorials. Once you have these tools in place, you are ready to proceed with the tutorial. See below for examples of each integrated with LangChain. Picking up a LLM Using LangChain will usually require integrations with one or more model providers, data stores, apis, etc. First, how to query GPT. Keywords are the words and phrases that users type into search engines when they’re looking for information. Higher values like 0. It uses the getDocument function from the PDF. Installation # To get started, install. Parameters blob - Blob instance Returns List of documents Examples using LanguageParser ¶ Source Code. It enables applications that are: Data-aware: connect a language model to other sources of data; Agentic: allow a language model to interact with its environment; The main value props of LangChain are: Components: abstractions for working with language. Jul 26, 2023 6 min read. You can do this in the terminal by running: mkdir quote-scraper. An LLM agent consists of three parts: PromptTemplate: This is the prompt template that can be used to instruct the language model on what to do. On that date, we will remove functionality from langchain. Mostly, these loaders input data from files but sometime from URLs. lc_attributes (): undefined | SerializedFields. In this video, I give an overview of Structured Output parsers with Langchain and discuss some of their use cases. llms import. In this post we briefly discuss how LangChain can be used with Azure OpenAI Service. LangChain supports various popular LLM architectures, such as GPT-3, enabling developers to work with state-of-the-art models for their applications. This article will provide an introduction to LangChain LLM. Format for Elastic Cloud URLs is https://username. It is a great tool for organizing, analyzing, and presenting data. Conversational Retrieval QA. environ ["OPENAI_API_KEY"] = "YOUR-API-KEY". The core idea of the library is that we. SQL Database Agent #. Getting Started; LLMs. #2 Prompt Templates for GPT 3. LangChain is a framework that enables quick and easy development of applications that make use of Large Language Models, for example, GPT-3. This is a convenience method for interactive development environment. They may look old-fashioned, but they are durable and versatile Expert Advice On Improving Your Home Videos Latest View All Guides Latest View All Radi. libclang provides a cursor-based API to the abstract syntax. Basics: What is Langchain. Jun 14, 2023 · This tutorial gives you a quick walkthrough about building an end-to-end language model application with LangChain. schema import BaseOutputParser. Step 3: Split the document into pieces. unstructured-api-tools - Library that converts pipeline notebooks to. A map of additional attributes to merge with constructor args. Contribute to jordddan/langchain- development by creating an account on GitHub. Colab: https://drp. Output parsers are classes that help structure language model responses. Get started Quickstart Quickstart Installation To install LangChain run: npm Yarn pnpm npm install -S langchain For more details, see our Installation guide. A PromptTemplate is responsible for the construction of this input. parse ( text: string ): Promise < Record < string, string > >. When working with any language model, we need the ability to interface with it. Values are the attribute values, which will be serialized. But don’t worry – with this tutorial, you’ll be up to speed in no time. Note that the `llm-math` tool uses an LLM, so we need to pass that in. First, install the dependencies. Output parsers are classes that help structure language model responses. ipynb Merge pull request #31 from ipsorakis/patch-1. I plan to explore other parsers in the fut. Higher values like 0. Agents expose an interface that takes in user input along with a list of previous steps the agent has taken, and returns either an AgentAction or AgentFinish. You should be able to use the parser to parse the output of the chain. 🦜🔗 LangChain 0. This output parser allows users to specify an arbitrary JSON schema and query LLMs for JSON outputs that conform to that schema. LangChain is an open-source framework designed to simplify the creation of applications using large language models (LLMs). Chains may consist of multiple components from. This documentation is organized into four sections (according to the Diátaxis documentation framework ). How to use the async API for LLMs; How to write a custom LLM wrapper;. Tools are functions or pydantic classes agents can use to connect with the outside world. This notebook shows how to use the Postgres vector database ( PGVector ). You’ll also learn how to create a frontend chat interface to display the results alongside source documents. Java version of LangChain, while empowering LLM for Big Data. Unstructured File. Agentic: allow a language model to interact with its environment. parse (blob: Blob) → List [Document] ¶ Eagerly parse the blob into a document or documents. Chroma is a AI-native open-source vector database focused on developer productivity and happiness. Specify the schema of what should be extracted and provide some examples. Mostly, these loaders input data from files but sometime from URLs. Wraps a parser and tries to fix parsing errors. agents import tool import. This tutorial gives you a quick walkthrough about building an end-to-end language model application with LangChain. This adaptability makes LangChain ideal for constructing AI applications across various scenarios and sectors. This documentation page outlines the essential components of the system and guides. Action: python_repl_ast ['df']. To obtain your Elastic Cloud password for the default “elastic” user: Log in to the Elastic Cloud console at https://cloud. langchain, a framework for working with LLM models. In this step-by-step tutorial, we will guide you through the various features and functionalities of your Affirm ac. This notebook shows how to use an Enum output parser. from langchain. Contribute to jordddan/langchain- development by creating an account on GitHub. This means they support invoke, ainvoke, stream, astream, batch, abatch, astream_log calls. run, description = "useful for. A map of additional attributes to merge with constructor args. To fine tune or not to fine tune? We need a way to teach GPT-3 about the technical details of the Dagster GitHub project. LangChain provides several classes and functions to make constructing and working with prompts. With Language Servers, you can implement autocomplete, error-checking (diagnostics), jump-to-definition, and many other language features supported in VS Code. One new way of evaluating them is using language models themselves to do the evaluation. Open Source LLMs. May 14, 2023 · Output parser. class BasePDFLoader(BaseLoader, ABC): """Base loader class for PDF files. This post will look at 3 ways to query Strava data with LangChain's OpenAPI, Pandas Dataframe, and CSV agents with the Strava API in Python. In the next step, we have to import the HuggingFacePipeline from Langchain. get_format_instructions → str [source] #. langchain, a framework for working with LLM models. Open Source LLMs. In this video, I give an overview of Structured Output parsers with Langchain and discuss some of their use cases. npm install --save next react react-dom. By leveraging the power of LangChain, SQL Agents, and OpenAI's Large Language Models (LLMs) like ChatGPT, we can create applications that enable users to query databases using natural language. Brian Wang is a Futurist Thought Leader and a popular Science blogger with 1 million readers per month. output_parser command_list = parser. , some pieces of text). schema import BaseOutputParser. Reload to refresh your session. We would like to show you a description here but the site won’t allow us. Chat models are a variation on language models. For example, to create a bot that can translate from English to French:. Keys are the attribute names, e. For example, this release addressed multiple issues with libxml2 (an XML C parser), including buffer overflows, arb. Chat Messages. This notebook shows how to use the Postgres vector database ( PGVector ). Picking up a LLM Using LangChain will usually require integrations with one or more model providers, data stores, apis, etc. First, you need to set up a Google Cloud Storage (GCS. In the next step, we have to import the HuggingFacePipeline from Langchain. This output parser can be used when you want to return multiple fields. darth powell
Install Chroma with: pip install chromadb. . Langchain parser tutorial
Step 4: Generate embeddings. Step 5: Constructing the LLM Chain. If you aren't concerned about being a good citizen, or you control the server you are scraping and don't care about load, you can change the requests_per_second parameter to. We've fielded a lot of questions about the latency of LangChain applications - where it comes from, how to improve. Pinecone is a vectorstore for storing embeddings and your PDF in text to later retrieve. import { OpenAI } from "langchain/llms/openai"; import { PromptTemplate } from "langchain/prompts"; import {. In this step-by-step tutorial, we will guide you through the various features and functionalities of your Affirm ac. Note that, as this agent is in active development, all. You’ll learn how to create a simple document in just a few easy steps. 0) By default, LangChain creates the chat model with a temperature value of 0. LangChain makes it easy to manage interactions with language models. It's offered in Python or JavaScript (TypeScript) packages. May 30, 2023 · In this article, I will introduce LangChain and explore its capabilities by building a simple question-answering app querying a pdf that is part of Azure Functions Documentation. It provides abstractions in the form of components to use LLMs in a more efficient or programmatic way. py uses LangChain tools to parse the document and create embeddings locally using HuggingFaceEmbeddings (SentenceTransformers). Calls the parser with a given input and optional configuration options. As you’re looking through this tutorial, examine 👀 the outputs carefully to understand what errors are being made. Use Redis to cache prompts and responses. Values are the attribute values, which will be serialized. Normally, there is no way an LLM would know such recent information, but using LangChain, I made Talkie search on the Internet and responded. # Create the LLM Chain. parse(misformatted) Actor (name='Tom Hanks',. 7 will make the output more random. display import Markdown, display. llms import. from detectron2. If you’re looking to get started with Microsoft Publisher, this tutorial is for you. If you're looking to harness the power of large language models for your data, this is the video for you. Once the code is executed, the output of the code is printed. With its intricate knotting techniques and stunning designs, it’s no wonder that macrame has seen a resurgence in popularity in recent years. js library to load the PDF from the buffer. As you may know, GPT models have been trained on data up until 2021, which can be a significant limitation. Instead, we can use the RetryOutputParser, which passes in the prompt (as well as the original output) to try again to get a better response. LangChain cookbook. I plan to explore other parsers in the fut. LangChain is an AI Agent tool that adds functionality to large language models (LLMs) like GPT. Whether you are a beginner or an experienced quilter, their tutorials offer a wealth of knowledge and inspiration. py and start with some imports:. Installation and Setup To get started, follow the installation. LangChain is an AI Agent tool that adds functionality to large language models (LLMs) like GPT. load_and_split ( [text_splitter]) Load Documents and split into chunks. Looking for a helpful read on writing a better resume, but can't get around pulling up everyone else's resumes instead? Search PDF is a custom Google search that filters up books and instructional PDFs. LangChain also allows for connecting external data sources and integration with many LLMs available on the market. Are you looking to engage with your audience and establish a strong connection with them? One of the most effective ways to achieve this is by creating a newsletter. OutputParser: This determines how to parse. Keep in mind that large language models are leaky abstractions! You'll have to use an LLM with sufficient capacity to generate well-formed JSON. * Chat history will be an empty string if it's the first question. How-to Use with LLMChains Use with LLMChains For convenience, you can add an output parser to an LLMChain. It enables applications that are: Data-aware: connect a language model to other sources of data; Agentic: allow a language model to interact with its environment; The main value props of LangChain are: Components: abstractions for working with language. Cassandra Chat Message History. Example run. This sections shows results of using the refine Chain to do question answering with sources. Finally, to the point, first of course we need to allow config files on the command line. ipynb fixing agents url last week LangChain Cookbook Part 2 - Use Cases. In this step-by-step tutorial, we will guide you through the various features and functionalities of your Affirm ac. Before we dive into the tutorial, let’s explore why using a free payroll calculat. Instructions on how. DateTime parser — Parses a datetime string into a Python datetime object. Models I/O. These LLMs are specifically designed to handle unstructured text data and. Step 3: Split the document into pieces. com/pythonGet the code: https://github. There are reasonable limits to concurrent requests, defaulting to 2 per second. 5 more agentic and data-aware. The first example uses only a custom prompt prefix and suffix, which is simpler to start. There are two main methods an output parser must implement: get_format_instructions() -> str:. User: I am looking for X. A map of additional attributes to merge with constructor args. These attributes need to be accepted by the constructor as arguments. A tutorial of the six core modules of the LangChain Python package covering models, prompts, chains, agents, indexes, and memory with OpenAI and. As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of updating code, better documentation, or project to feature. Keep in mind that large language models are leaky abstractions! You'll have to use an LLM with sufficient capacity to generate well-formed JSON. LangChain’s document loaders, index-related chains, and output parser help load and parse the data to generate results. May 22, 2023 · In this tutorial, you will learn how it works using Python examples. Output is streamed as Log objects, which include a list of jsonpatch ops that describe how the state of the run has changed in each step, and the final state of the run. These attributes need to be accepted by the constructor as arguments. 1 and <4. This work is extremely related to output parsing. May 9, 2023 · Installation. LangChain provides a standard interface, lots of integrations, and end-to-end chains for common applications. This notebook goes through how to create your own custom LLM agent. Are you looking to become a quilting expert? Look no further than Missouri Star Quilt Tutorials. For this getting started tutorial, we look at two primary examples of LangChain usage. Chat models accept List [BaseMessage] as inputs, or objects which can be coerced to messages, including str (converted to HumanMessage. js library, you need to include it as a dependency in your project. See all available Document Loaders. These attributes need to be accepted by the constructor as arguments. See the accompanying tutorials on YouTube. I've been using the Langchain library, UnstructuredFileLoader from langchain. Getting started with Azure Cognitive Search in LangChain. You switched accounts on another tab or window. config import get_cfg. This idea is largely inspired by BabyAGI and then the “Plan-and-Solve” paper. This notebook showcases an agent designed to interact with a SQL databases. LangChain is an open-source developer framework for building LLM applications. tools = load_tools ( ['python_repl'], llm=llm) # Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use. Installation and Setup To get started, follow the installation instructions to install LangChain. The ChatGPT clone, Talkie, was written on 1 April 2023, and the video was made on 2 April. com/GregKamradtNewsletter: https://mail. llms import OpenAI. Showing Step (1) Extract the Book Content (highlight in red). Setup model and AutoGPT #. js environments. This allows the inner run to be tracked by. It provides abstractions in the form of components to use LLMs in a more efficient or programmatic way. from_llm(parser=parser, llm=ChatOpenAI()) new_parser. streamLog () Stream all output from a runnable, as reported to the callback system. JSON Lines is a file format where each line is a valid JSON value. Follow the prompts to reset the password. Interacting with APIs LangChain’s chain and agent features enable users to include LLMs in a longer workflow with other API calls. There are two main methods an output parser must implement: "Get format instructions": A method which returns a string containing instructions for how the output of a language model should be formatted. A map of additional attributes to merge with constructor args. First, how to query GPT. Tech stack used includes LangChain, Pinecone, Typescript, Openai, and Next. There are two types of sequential chains: SimpleSequentialChain: The simplest form of sequential chains, where each step has a singular input/output, and the output of one step is the input to the next. For this example, we'll use OpenAI's model APIs. In today’s digital age, having an email account is essential for communication, whether it’s for personal or professional use. Extract the text from a pdf document and process it. Python Docs K API reference langchain/ output_parsers Classes RegexParser RegexParser Class to parse the output of an LLM call into a dictionary. be/vGP4pQdCocwWild Belle - Keep You: ht. No need to subclass: output = chain. There are two main methods an output parser must implement: "Get format instructions": A method which returns a string containing instructions for how the output of a language model should be formatted. Create embeddings from this text. Within the Flowise Marketplaces, select the Antonym flow. Custom LLM agent. To run these examples, you'll need an OpenAI account and API key ( create a free account ). In order to create a custom chain: Start by subclassing the Chain class, Fill out the input_keys and output_keys properties, Add the _call method that shows how to execute the chain. This input is often constructed from multiple components. In addition, it includes functionality such as token management and context management. . virtual learning academy answer key, jobs in san diego california, debugging and solving software problems qwiklabs, hypnopimp, twinks on top, dallas craigslist cars for under 4000 cash by owner, porn gay brothers, centene holiday schedule 2022, starpath asa 105, greenwich village restaurants 1980s, feminized hypnosis, salem or craigslist co8rr