add readme requirements

Dockerfile

@@ -0,0 +1,34 @@
+FROM langchain/langchain:latest 
+
+
+# Update packages and install nano and curl
+RUN apt-get update -y 
+RUN apt-get install nano curl -y
+
+# THIS IS SPECIFIC TO HUGGINFACE
+# We create a new user named "user" with ID of 1000
+RUN useradd -m -u 1000 user
+# We switch from "root" (default user when creating an image) to "user" 
+USER user
+# We set two environmnet variables 
+# so that we can give ownership to all files in there afterwards
+# we also add /home/user/.local/bin in the $PATH environment variable 
+# PATH environment variable sets paths to look for installed binaries
+# We update it so that Linux knows where to look for binaries if we were to install them with "user".
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# We set working directory to $HOME/app (<=> /home/user/app)
+WORKDIR $HOME/app
+
+# Copy all local files to /home/user/app with "user" as owner of these files
+# Always use --chown=user when using HUGGINGFACE to avoid permission errors
+COPY --chown=user . $HOME/app
+
+# Install all dependencies
+RUN pip install -r requirements.txt
+# make sure all packages are up to date
+RUN pip install --upgrade -r requirements.txt
+
+# Run FastAPI
+CMD fastapi run app.py --port 7860

README.md

@@ -10,3 +10,26 @@ short_description: Very simple langchain api to translate anything
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Langchain basics 
+
+This is a basic application that runs an LLM application using Langchain and Langserve. 
+
+## Requirements 
+
+You need to have:
+
+* Mistral Account to get a Mistral API Key
+* Docker installed
+
+## Run the application 
+
+To run the application simply:
+
+```bash
+docker run -p 7860:7680 -e MISTRAL_API_KEY=REPLACE_WITH_YOUR_MISTRAL_API_KEY jedha/langchain-base
+```
+And then open web browser and go to:
+
+* http://localhost:7860/chain/playground 
+
+This endpoint will prompt you to a web page to test the `/chain` endpoint.

app.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+from fastapi import FastAPI
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain_mistralai import ChatMistralAI
+from langserve import add_routes
+
+# 1. Create prompt template
+# Here we create a simple prompt with two inputs 
+# First a "system" prompt that corresponds to the instruction for the model 
+# Second a "user" prompt that corresponds to what a user inputs when interacting with the model
+system_template = "Translate the following into {language}:"
+prompt_template = ChatPromptTemplate.from_messages([
+    ('system', system_template),
+    ('user', '{text}')
+])
+
+# 2. Create model
+# Here we chose a model from Mistral
+# Generally you should always try to use Chat models even if the purpose of the app is not to chat
+model = ChatMistralAI(model="mistral-large-latest")
+
+# 3. Create parser
+# This simply outputs the result of the LLM as pure string
+parser = StrOutputParser()
+
+# 4. Create chain
+# Here we create a workflow that 
+# First -> Read the prompt 
+# Second -> Apply the model on the given prompt 
+# Third -> Output the result as a string 
+chain = prompt_template | model | parser
+
+# 5. App definition
+# Here we instanciate a FastAPI application
+app = FastAPI(
+  title="LangChain Server",
+  version="1.0",
+  description="A simple API server using LangChain's Runnable interfaces",
+)
+
+# 6. Adding chain route
+# Finally this is a LangServe Wrapper that creates a endpoint at /chain 
+# with a playground that you can play with at /chain/playground when the server is up
+add_routes(
+    app,
+    chain,
+    path="/chain",
+)

requirements.txt

@@ -0,0 +1,7 @@
+langchain
+langchain-community 
+langchain-mistralai
+langchain-openai
+langserve[all]
+langgraph
+fastapi[standard]