add usage readmes

prompts/api/api_response/README.md

@@ -0,0 +1,35 @@
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import APIChain
+
+llm = ...
+api_docs = ...
+prompt = load_from_hub('api/api_response/<file-name>')
+chain = APIChain.from_llm_and_api_docs(llm, api_docs, api_response_prompt=prompt)
+```
+

prompts/api/api_url/README.md

@@ -0,0 +1,35 @@
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import APIChain
+
+llm = ...
+api_docs = ...
+prompt = load_from_hub('api/api_url/<file-name>')
+chain = APIChain.from_llm_and_api_docs(llm, api_docs, api_url_prompt=prompt)
+```
+

prompts/conversation/basic/README.md

@@ -0,0 +1,34 @@
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import ConversationChain
+
+llm = ...
+prompt = load_from_hub('conversation/basic/<file-name>')
+chain = ConversationChain(llm=llm, prompt=prompt)
+```
+

prompts/conversation/summarize/README.md

@@ -0,0 +1,36 @@
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import ConversationChain
+from langchain.chains.conversation.memory import ConversationSummaryMemory
+
+llm = ...
+prompt = load_from_hub('conversation/summarize/<file-name>')
+memory = ConversationSummaryMemory(llm=llm, prompt=prompt)
+chain = ConversationChain(llm=llm, memory=memory)
+```
+

prompts/hello-world/README.md

@@ -1,27 +1,34 @@
-# Hello World
-> A simple prompt as an example
+<!-- Add a template for READMEs that capture the utility of prompts -->
 
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
 
-## Configuration
-- input_variables: []
-  - There are no inputs
-- output_parser: null
-  - There is no output parsing needed
-- template: 'Say hello world.'
-  - Just a simple hello.
-template_format: f-string
-  - We use standard f-string formatting here.
 
 ## Usage
 
-Ex:
-```python3
+Below is a code snippet for how to use the prompt.
+
+```python
 from langchain.prompts import load_from_hub
-from langchain.llms import OpenAI
-from langchain.prompts.loading import load_prompt
+from langchain.chains import LLMChain
 
-llm = OpenAI(temperature=0.9)
-# prompt = load_from_hub("hello-world/prompt.yaml")
-output = llm(prompt.format())
-print(output)
+llm = ...
+prompt = load_from_hub('hello-world/<file-name>')
+chain = LLMChain(llm=llm, prompt=prompt)
 ```
+

prompts/llm_bash/README.md

@@ -1,9 +1,34 @@
-A prompt to generate bash commands given natural language objectives.
+<!-- Add a template for READMEs that capture the utility of prompts -->
 
-Inputs:
-1. question
+# Description of {{prompt}}
 
+{{High level text description of the prompt, including use cases.}}
 
 ## Compatible Chains
 
-1. `chains/llm_bash/LLMBashChain`
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import LLMBash
+
+llm = ...
+prompt = load_from_hub('llm_bash/<file-name>')
+chain = LLMBash(llm=llm, prompt=prompt)
+```
+

prompts/llm_math/README.md

@@ -0,0 +1,34 @@
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import LLMMathChain
+
+llm = ...
+prompt = load_from_hub('llm_math/<file-name>')
+chain = LLMMathChain(llm=llm, prompt=prompt)
+```
+

prompts/pal/README.md

@@ -1,4 +1,36 @@
-Answer a math question in python.
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import PALChain
+
+llm = ...
+stop = ...
+get_answer_expr = ...
+prompt = load_from_hub('pal/<file-name>')
+chain = PALChain(llm=llm, prompt=prompt, stop=stop, get_answer_expr=get_answer_expr)
+```
 
-Inputs:
-1. question

prompts/qa/map_reduce/question/README.md

@@ -1,3 +1,34 @@
-This prompt is a basic implementation of a question answering prompt for a map-reduce chain.
-Specifically, it is the "map" prompt that gets applied to all input documents.
-It takes in a single variable for the document (`context`) and then a variable for the question (`question`)
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains.question_answering import load_qa_chain
+
+llm = ...
+prompt = load_from_hub('qa/map_reduce/question/<file-name>')
+chain = load_qa_chain(llm, chain_type="map_reduce", question_prompt=prompt)
+```
+

prompts/qa/map_reduce/reduce/README.md

@@ -1,3 +1,34 @@
-This prompt is a basic implementation of a question answering prompt for a map-reduce chain.
-Specifically, it is the "reduce" prompt that gets applied documents after they have initially been asked for an answer.
-It takes in a single variable for the initial responses (`summaries`) and then a variable for the question (`question`)
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains.question_answering import load_qa_chain
+
+llm = ...
+prompt = load_from_hub('qa/map_reduce/reduce/<file-name>')
+chain = load_qa_chain(llm, chain_type="map_reduce", combine_prompt=prompt)
+```
+

prompts/qa/refine/README.md

@@ -1,6 +1,34 @@
-This prompt refines an existing answer to a question given context, with additional instructions to update the sources used.
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains.question_answering import load_qa_chain
+
+llm = ...
+prompt = load_from_hub('qa/refine/<file-name>')
+chain = load_qa_chain(llm, chain_type="refine", refine_prompt=prompt)
+```
 
-The inputs are:
-1. question
-2. existing_answer
-3. context_str

prompts/qa/stuff/README.md

@@ -1,6 +1,34 @@
-This is a question answering prompt for a "stuff" chain that cites sources.
-It takes variables for all the documents (`context`) and then a variable for the question (`question`)
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
 
 ## Compatible Chains
 
-1. `chains/qa_with_sources`
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains.question_answering import load_qa_chain
+
+llm = ...
+prompt = load_from_hub('qa/stuff/<file-name>')
+chain = load_qa_chain(llm, chain_type="stuff", prompt=prompt)
+```
+

prompts/sql_query/language_to_sql_output/README.md

@@ -1,6 +1,35 @@
-This prompt takes a natural language question, converts the question into a SQL query, executes the query and gets the result, and finally returns the final answer to the user.
+<!-- Add a template for READMEs that capture the utility of prompts -->
 
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
 
 ## Compatible Chains
 
-1. `chains/sql_database.py`
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import SQLDatabaseChain
+
+llm = ...
+database = ...
+prompt = load_from_hub('sql_query/language_to_sql_output/<file-name>')
+chain = SQLDatabaseChain(llm=llm, database=database, prompt=prompt)
+```
+

prompts/sql_query/relevant_tables/README.md

@@ -1,6 +1,35 @@
-This prompt takes a question and a list of potential tables, and determines which tables in a database would be most relevant.
+<!-- Add a template for READMEs that capture the utility of prompts -->
 
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
 
 ## Compatible Chains
 
-1. `chains/sql_database.py`
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains import SQLDatabaseSequentialChain
+
+llm = ...
+database = ...
+prompt = load_from_hub('sql_query/relevant_tables/<file-name>')
+chain = SQLDatabaseSequentialChain.from_llm(llm, database, decider_prompt=prompt)
+```
+

prompts/summarize/README.md

@@ -1,9 +0,0 @@
-# Summarize
-This is a type of chain to distill large amounts of information into a small amount.
-
-There are three types of summarize chains:
-1. Stuff: This is a simple chain to stuff all the text from each document into one propmt. This is limited by token window so this approach only works for smaller amounts of data.
-2. Map Reduce: This maps a summarize prompt onto each data chunk and then combines all the outputs to finally reduce using a summarization prompt.
-3. Refine: This iteratively passes in each chunk of data and update a continously update an evolving summary to be more accurate based on the new chunk of data given.
-
-## Usage

prompts/summarize/map_reduce/README.md

@@ -1,2 +0,0 @@
-# Map Reduce
-This maps a summarize prompt onto each data chunk and then combines all the outputs to finally reduce using a summarization prompt.

prompts/summarize/map_reduce/map/README.md

@@ -0,0 +1,34 @@
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains.summarize import load_summarize_chain
+
+llm = ...
+prompt = load_from_hub('summarize/map_reduce/map/<file-name>')
+chain = load_summarize_chain(llm, chain_type="map_reduce", map_prompt=prompt)
+```
+

prompts/summarize/refine/README.md

@@ -1,2 +1,34 @@
-# Refine
-This iteratively passes in each chunk of data and update a continously update an evolving summary to be more accurate based on the new chunk of data given.
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains.summarize import load_summarize_chain
+
+llm = ...
+prompt = load_from_hub('summarize/refine/<file-name>')
+chain = load_summarize_chain(llm, chain_type="refine", refine_prompt=prompt)
+```
+

prompts/summarize/refine/chain.yaml

@@ -1,13 +0,0 @@
-# Prompt config for a chain?
-
-input_variables: ['text']
-output_parser: null
-# what primitives do we allow?
-template: [
-  map:
-    input: 'text'
-    prompt: 'prompt.yaml',
-  reduce:
-    prompt: 'promptSummarize.yaml'
-]
-template_format: f-string

prompts/summarize/refine/propmtSummary.yaml

@@ -1,10 +0,0 @@
-input_variables: [text]
-output_parser: null
-template: 'Write a concise summary of the following:
-
-
-{text}
-
-
-CONCISE SUMMARY:'
-template_format: f-string

prompts/summarize/stuff/README.md

@@ -1,2 +1,34 @@
-# Stuff
-This is a simple chain to stuff all the text from each document into one propmt. This is limited by token window so this approach only works for smaller amounts of data.
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
+
+
+## Usage
+
+Below is a code snippet for how to use the prompt.
+
+```python
+from langchain.prompts import load_from_hub
+from langchain.chains.summarize import load_summarize_chain
+
+llm = ...
+prompt = load_from_hub('summarize/stuff/<file-name>')
+chain = load_summarize_chain(llm, chain_type="stuff", prompt=prompt)
+```
+

prompts/vector_db_qa/README.md

@@ -1,19 +1,35 @@
-This prompt is a simple prompt that answers a question given some context. If the answer isn't provided in the context, then the prompt suggests the LLM to return `I don't know`.
+<!-- Add a template for READMEs that capture the utility of prompts -->
+
+# Description of {{prompt}}
+
+{{High level text description of the prompt, including use cases.}}
+
+## Compatible Chains
+
+Below is a list of chains we expect this prompt to be compatible with.
+
+1. {{Chain Name}}: {{Path to chain in module}}
+2. ...
+
+## Inputs
+
+This is a description of the inputs that the prompt expects.
+
+1. {{input_var}}: {{Description}}
+2. ...
 
 
 ## Usage
 
-```
+Below is a code snippet for how to use the prompt.
+
+```python
 from langchain.prompts import load_from_hub
-from langchain.llms import OpenAI
-from langchain.prompts.loading import load_prompt
+from langchain.chains import VectorDBQA
 
-llm = OpenAI(temperature=0.9)
-prompt = load_from_hub("vector_db_qa/prompt.py")
-output = llm(prompt.format(context="...", question="..."))
-print(output)
+llm = ...
+vectorstore = ...
+prompt = load_from_hub('vector_db_qa/<file-name>')
+chain = VectorDBQA.from_llm(llm, prompt=prompt, vectorstore=vectorstore)
 ```
 
-## Compatible Chains
-
-1. `chains/vector_db_qa`