Change Pipeline's name & Fix dense qa config & Add FAQ (#3202)

Author: w5688414

pipelines/FAQ.md

@@ -123,3 +123,7 @@ python 3.7版本引起的错误，修改如下代码：
 # 增加batch_size参数，传入一个数值即可
 document_store.update_embeddings(retriever, batch_size=256)
 ```
+
+#### 运行后台程序出现了错误：`Exception: Failed loading pipeline component 'DocumentStore': RequestError(400, 'illegal_argument_exception', 'Mapper for [embedding] conflicts with existing mapper:\n\tCannot update parameter [dims] from [312] to [768]')`
+
+以语义检索为例，这是因为模型的维度不对造成的，请检查一下 `elastic search`中的文本的向量的维度和`semantic_search.yaml`里面`DocumentStore`设置的维度`embedding_dim`是否一致，如果不一致，请重新使用`utils/offline_ann.py`构建索引。总之，请确保构建索引所用到的模型和`semantic_search.yaml`设置的模型是一致的。

pipelines/README.md

@@ -57,7 +57,7 @@ Note: 因为 pipelines 依赖较多, 安装耗时大概 10 分钟左右，安装
 - Docker 18.03 以上
 ### pip 安装
 ```
-pip install --upgrade pipelines
+pip install --upgrade paddle-pipelines
 ```
 
 ### 源码安装

pipelines/rest_api/pipeline/dense_qa.yaml

@@ -6,14 +6,15 @@ components:    # define all the building-blocks for Pipeline
     params:
       host: localhost
       index: baike_cities
+      embedding_dim: 312
       port: 9200
   - name: Retriever
     type: DensePassageRetriever
     params:
       document_store: DocumentStore    # params can reference other components defined in the YAML
       top_k: 10
-      query_embedding_model: rocketqa-zh-dureader-query-encoder
-      passage_embedding_model: rocketqa-zh-dureader-query-encoder
+      query_embedding_model: rocketqa-zh-nano-query-encoder
+      passage_embedding_model: rocketqa-zh-nano-query-encoder
       embed_title: False
   - name: Ranker       # custom-name for the component; helpful for visualization & debugging
     type: ErnieRanker    # pipelines Class name for the component

pipelines/setup.py

@@ -22,7 +22,7 @@
 with open("requirements.txt") as fin:
     REQUIRED_PACKAGES = fin.read()
 
-setuptools.setup(name="pipelines",
+setuptools.setup(name="paddle-pipelines",
                  version=pipelines.__version__,
                  author="PaddlePaddle Speech and Language Team",
                  author_email="[email protected]",

pipelines/utils/offline_ann.py

@@ -10,7 +10,9 @@
 data_dict = {
     'data/dureader_dev':
     "https://paddlenlp.bj.bcebos.com/applications/dureader_dev.zip",
-    "data/baike": "https://paddlenlp.bj.bcebos.com/applications/baike.zip"
+    "data/baike": "https://paddlenlp.bj.bcebos.com/applications/baike.zip",
+    "data/insurance":
+    "https://paddlenlp.bj.bcebos.com/applications/insurance.zip"
 }
 
 parser = argparse.ArgumentParser()