Update README.md (#748)

Signed-off-by: Liangyx2 <yuxiang.liang@intel.com>

Author: Liangyx2

intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/README.md

@@ -27,7 +27,7 @@ In addition, our plugin seamlessly integrates the online embedding model, Google
 
 The workflow of this plugin consists of three main operations: document indexing, intent detection, and retrieval. The `Agent_QA` initializes itself using the provided `input_path` to construct a local database. During a conversation, the user's query is first passed to the `IntentDetector` to determine whether the user intends to engage in chitchat or seek answers to specific questions. If the `IntentDetector` determines that the user's query requires an answer, the retriever is activated to search the database using the user's query. The documents retrieved from the database serve as reference context in the input prompt, assisting in generating responses using the Large Language Models (LLMs). 
 
-We have already provided support for popular file farmat on retrieval. When using xlsx, csv, json/jsonl, predefined structure should be used.
+We have already provided support for popular file format on retrieval. When using xlsx, csv, json/jsonl, predefined structure should be used.
 | File Type | Predefined Structure |
 | :----: | :----: |
 | xlsx | ['Questions', 'Answers']<br>['question', 'answer', 'link']<br>['context', 'link'] |