template: Update Vectara templates (#15363)

fixed multi-query template for Vectara
added self-query template for Vectara

Also added prompt_name parameter to summarization

CC @efriis 
 **Twitter handle:** @ofermend

libs/community/langchain_community/vectorstores/vectara.py

@@ -22,11 +22,14 @@ class SummaryConfig:
     is_enabled: True if summary is enabled, False otherwise
     max_results: maximum number of results to summarize
     response_lang: requested language for the summary
+    prompt_name: name of the prompt to use for summarization
+      (see https://docs.vectara.com/docs/learn/grounded-generation/select-a-summarizer)
     """
 
     is_enabled: bool = False
     max_results: int = 7
     response_lang: str = "eng"
+    prompt_name: str = "vectara-summary-ext-v1.2.0"
 
 
 @dataclass
@@ -364,6 +367,7 @@ class Vectara(VectorStore):
                 {
                     "maxSummarizedResults": config.summary_config.max_results,
                     "responseLang": config.summary_config.response_lang,
+                    "summarizerPromptName": config.summary_config.prompt_name,
                 }
             ]
 
@@ -570,6 +574,7 @@ class VectaraRetriever(VectorStoreRetriever):
             "k": 5,
             "filter": "",
             "n_sentence_context": "2",
+            "summary_config": SummaryConfig(),
         }
     )
 

templates/rag-vectara-multiquery/README.md

@@ -23,20 +23,20 @@ pip install -U langchain-cli
 To create a new LangChain project and install this as the only package, you can do:
 
 ```shell
-langchain app new my-app --package rag-vectara
+langchain app new my-app --package rag-vectara-multiquery
 ```
 
 If you want to add this to an existing project, you can just run:
 
 ```shell
-langchain app add rag-vectara
+langchain app add rag-vectara-multiquery
 ```
 
 And add the following code to your `server.py` file:
 ```python
 from rag_vectara import chain as rag_vectara_chain
 
-add_routes(app, rag_vectara_chain, path="/rag-vectara")
+add_routes(app, rag_vectara_chain, path="/rag-vectara-multiquery")
 ```
 
 (Optional) Let's now configure LangSmith. 
@@ -61,12 +61,12 @@ This will start the FastAPI app with a server is running locally at
 [http://localhost:8000](http://localhost:8000)
 
 We can see all templates at [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)
-We can access the playground at [http://127.0.0.1:8000/rag-vectara/playground](http://127.0.0.1:8000/rag-vectara/playground)  
+We can access the playground at [http://127.0.0.1:8000/rag-vectara-multiquery/playground](http://127.0.0.1:8000/rag-vectara-multiquery/playground)  
 
 We can access the template from code with:
 
 ```python
 from langserve.client import RemoteRunnable
 
-runnable = RemoteRunnable("http://localhost:8000/rag-vectara")
+runnable = RemoteRunnable("http://localhost:8000/rag-vectara-multiquery")
 ```

templates/rag-vectara-multiquery/rag_vectara_multiquery/chain.py

@@ -41,7 +41,6 @@ retriever = MultiQueryRetriever.from_llm(retriever=vectara_retriever, llm=llm)
 # We extract the summary from the RAG output, which is the last document
 # (if summary is enabled)
 # Note that if you want to extract the citation information, you can use res[:-1]]
-model = ChatOpenAI()
 chain = (
     RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
     | (lambda res: res[-1])