Reorganize readme, add documentation to config hash endpoints (#241)

* Re organize some sections in the readme
* Use more highlighting in the readme for sections where attention is
required
* Expand doc-strings for config hash endpoints 
 

![image](https://github.com/langchain-ai/langserve/assets/3205522/9cfb8039-b9e6-4079-b677-d8a298575763)

README.md

@@ -40,6 +40,17 @@ We will be releasing a hosted version of LangServe for one-click deployments of
 ## Security
 
 * Vulnerability in Versions 0.0.13 - 0.0.15 -- playground endpoint allows accessing arbitrary files on server. [Resolved in 0.0.16](https://github.com/langchain-ai/langserve/pull/98).
+
+## Installation
+
+For both client and server:
+
+```bash
+pip install "langserve[all]"
+```
+
+or `pip install "langserve[client]"` for client code, and `pip install "langserve[server]"` for server code.
+
 
 ## LangChain CLI 🛠️
 
@@ -110,17 +121,16 @@ if __name__ == "__main__":
 
 If you've deployed the server above, you can view the generated OpenAPI docs using:
 
+> ⚠️ If using pydantic v2, docs will not be generated for invoke/batch/stream/stream_log. See [Pydantic](#pydantic) section below for more details.
+
 ```sh
 curl localhost:8000/docs
 ```
 
 make sure to **add** the `/docs` suffix. 
 
-Below will return a 404 until you define a `@app.get("/")`
-
-```sh
-localhost:8000
-```
+> ⚠️ Index page `/` is not defined by **design**, so `curl localhost:8000` or visiting the URL
+> will return a 404. If you want content at `/` define an endpoint `@app.get("/")`.
 
 ### Client
 
@@ -245,29 +255,13 @@ In addition, for configurable runnables, the playground will allow you to config
 <img src="https://github.com/langchain-ai/langserve/assets/3205522/86ce9c59-f8e4-4d08-9fa3-62030e0f521d" width="50%">
 </p>
 
-## Installation
-
-For both client and server:
-
-```bash
-pip install "langserve[all]"
-```
-
-or `pip install "langserve[client]"` for client code, and `pip install "langserve[server]"` for server code.
-
 ## Legacy Chains
 
 LangServe works with both Runnables (constructed via [LangChain Expression Language](https://python.langchain.com/docs/expression_language/)) and legacy chains (inheriting from `Chain`).
 However, some of the input schemas for legacy chains may be incomplete/incorrect, leading to errors.
 This can be fixed by updating the `input_schema` property of those chains in LangChain.
 If you encounter any errors, please open an issue on THIS repo, and we will work to address it.
 
-## Handling Authentication
-
-If you need to add authentication to your server,
-please reference FastAPI's [security documentation](https://fastapi.tiangolo.com/tutorial/security/)
-and [middleware documentation](https://fastapi.tiangolo.com/tutorial/middleware/).
-
 ## Deployment
 
 ### Deploy to GCP
@@ -289,6 +283,13 @@ Except for these limitations, we expect the API endpoints, the playground and an
 
 ## Advanced
 
+## Handling Authentication
+
+If you need to add authentication to your server,
+please reference FastAPI's [security documentation](https://fastapi.tiangolo.com/tutorial/security/)
+and [middleware documentation](https://fastapi.tiangolo.com/tutorial/middleware/).
+
+
 ### Files
 
 LLM applications often deal with files. There are different architectures

langserve/server.py

@@ -534,7 +534,10 @@ def _route_name_with_config(name: str) -> str:
                 "name": route_tags_with_config[0],
                 "description": (
                     "Endpoints with a default configuration "
-                    "set by `config_hash` path parameter."
+                    "set by `config_hash` path parameter. "
+                    "Used in conjunction with share links generated using the "
+                    "LangServe UI playground. "
+                    "The hash is an LZString compressed JSON string."
                 ),
             },
         ]
@@ -1101,6 +1104,13 @@ async def feedback(feedback_create_req: FeedbackCreateRequest) -> Feedback:
             response_model=InvokeResponse,
             tags=route_tags_with_config,
             name=_route_name_with_config("invoke"),
+            description=(
+                "This endpoint is to be used with share links generated by the "
+                "LangServe playground. "
+                "The hash is an LZString compressed JSON string. "
+                "For regular use cases, use the /invoke endpoint without "
+                "the `c/{config_hash}` path parameter."
+            ),
         )
         @app.post(
             f"{namespace}/invoke",
@@ -1120,6 +1130,13 @@ async def _invoke_docs(
             response_model=BatchResponse,
             tags=route_tags_with_config,
             name=_route_name_with_config("batch"),
+            description=(
+                "This endpoint is to be used with share links generated by the "
+                "LangServe playground. "
+                "The hash is an LZString compressed JSON string. "
+                "For regular use cases, use the /batch endpoint without "
+                "the `c/{config_hash}` path parameter."
+            ),
         )
         @app.post(
             f"{namespace}/batch",
@@ -1139,6 +1156,13 @@ async def _batch_docs(
             include_in_schema=True,
             tags=route_tags_with_config,
             name=_route_name_with_config("stream"),
+            description=(
+                "This endpoint is to be used with share links generated by the "
+                "LangServe playground. "
+                "The hash is an LZString compressed JSON string. "
+                "For regular use cases, use the /stream endpoint without "
+                "the `c/{config_hash}` path parameter."
+            ),
         )
         @app.post(
             f"{namespace}/stream",
@@ -1198,6 +1222,13 @@ async def _stream_docs(
             include_in_schema=True,
             tags=route_tags_with_config,
             name=_route_name_with_config("stream_log"),
+            description=(
+                "This endpoint is to be used with share links generated by the "
+                "LangServe playground. "
+                "The hash is an LZString compressed JSON string. "
+                "For regular use cases, use the /stream_log endpoint without "
+                "the `c/{config_hash}` path parameter."
+            ),
         )
         @app.post(
             f"{namespace}/stream_log",