Update README.md for manual_extraction. (#115)

Author: badmonster0

README.md

@@ -95,6 +95,7 @@ Go to the [examples directory](examples) to try out with any of the examples, fo
 | [Text Embedding](examples/text_embedding) | Index text documents with embeddings for semantic search |
 | [Code Embedding](examples/code_embedding) | Index code embeddings for semantic search |
 | [PDF Embedding](examples/pdf_embedding) | Parse PDF and index text embeddings for semantic search |
+| [Manual Extraction](examples/manual_extraction) | Extract structured information from a manual using LLM |
 
 More coming and stay tuned! If there's any specific examples you would like to see, please let us know in our [Discord community](https://discord.com/invite/zpA9S2DR7s) 🌱.
 

examples/manual_extraction/README.md

@@ -1,10 +1,21 @@
-Simple example for cocoindex: extract structured information from a Markdown file.
+In this example, we
+
+*   Converts PDFs (generated from a few Python docs) into Markdown.
+*   Extract structured information from the Markdown using LLM.
+*   Use a custom function to further extract information from the structured output.
 
 ## Prerequisite
-[Install Postgres](https://cocoindex.io/docs/getting_started/installation#-install-postgres) if you don't have one.
+
+Before running the example, you need to:
+
+*   [Install Postgres](https://cocoindex.io/docs/getting_started/installation#-install-postgres) if you don't have one.
+*   Install / configure LLM API. In this example we use Ollama, which runs LLM model locally. You need to get it ready following [this guide](https://cocoindex.io/docs/ai/llm#ollama). Alternatively, you can also follow the comments in source code to switch to OpenAI, and [configure OpenAI API key](https://cocoindex.io/docs/ai/llm#openai) before running the example.
 
 ## Run
 
+
+### Build the index
+
 Install dependencies:
 
 ```bash
@@ -23,10 +34,18 @@ Update index:
 python manual_extraction.py cocoindex update
 ```
 
-Run:
+### Query the index
+
+After index is build, you have a table with name `modules_info`. You can query it any time, e.g. start a Postgres shell:
 
 ```bash
-python manual_extraction.py
+psql postgres://cocoindex:cocoindex@localhost/cocoindex
+```
+
+And run the SQL query:
+
+```sql
+SELECT filename, module_info->'title' AS title, module_summary FROM modules_info;
 ```
 
 ## CocoInsight 
@@ -35,5 +54,5 @@ CocoInsight is in Early Access now (Free) 😊 You found us! A quick 3 minute vi
 Run CocoInsight to understand your RAG data pipeline:
 
 ```
-python manual_extraction.py cocoindex server -c https://cocoindex.io/cocoinsight
+python manual_extraction.py cocoindex server -c https://cocoindex.io
 ```

examples/manual_extraction/manual_extraction.py

@@ -112,7 +112,7 @@ def manual_extraction_flow(flow_builder: cocoindex.FlowBuilder, data_scope: coco
 
     modules_index.export(
         "modules",
-        cocoindex.storages.Postgres(),
+        cocoindex.storages.Postgres(table_name="modules_info"),
         primary_key_fields=["filename"],
     )